{"id":92598,"url":"https://github.com/jalberty2018/awesome-comfyui","name":"awesome-comfyui","description":"A collection of awesome custom nodes for ComfyUI","projects_count":8890,"last_synced_at":"2026-09-25T09:00:26.633Z","repository":{"id":306857360,"uuid":"1027207461","full_name":"jalberty2018/awesome-comfyui","owner":"jalberty2018","description":"A collection of awesome custom nodes for ComfyUI","archived":false,"fork":false,"pushed_at":"2026-09-13T04:08:34.000Z","size":24254,"stargazers_count":49,"open_issues_count":0,"forks_count":4,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-09-13T06:24:08.180Z","etag":null,"topics":["ai","awesome-list","awesome-readme","comfyui","comfyui-custom-node","comfyui-nodes","generative-ai"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/jalberty2018.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"claude":null,"gemini":null,"cursor":null,"copilot":null,"dco":null,"cla":null,"disclosure":null}},"created_at":"2025-07-27T14:42:52.000Z","updated_at":"2026-09-13T04:08:37.000Z","dependencies_parsed_at":"2026-09-13T06:18:45.792Z","dependency_job_id":null,"html_url":"https://github.com/jalberty2018/awesome-comfyui","commit_stats":null,"previous_names":["jalberty2018/awesome-comfyui"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/jalberty2018/awesome-comfyui","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jalberty2018%2Fawesome-comfyui","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jalberty2018%2Fawesome-comfyui/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jalberty2018%2Fawesome-comfyui/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jalberty2018%2Fawesome-comfyui/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jalberty2018","download_url":"https://codeload.github.com/jalberty2018/awesome-comfyui/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jalberty2018%2Fawesome-comfyui/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":341189360,"owners_count":37670837,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-08-22T15:14:58.755Z","status":"online","status_checked_at":"2026-09-25T02:00:20.896Z","response_time":55,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"created_at":"2025-08-07T01:03:11.821Z","updated_at":"2026-09-25T09:00:26.633Z","primary_language":null,"list_of_lists":false,"displayable":true,"categories":["Workflows (3395) sorted by GitHub Stars","Workflows (3360) sorted by GitHub Stars","Workflows trending today","Workflows pushed today","Workflows created in 7 days","Workflows pushed in 7 days","Workflows (4534) sorted by GitHub Stars","Workflows (3658) sorted by GitHub Stars","Workflows created today","Workflows (3054) sorted by GitHub Stars","Workflows (3088) sorted by GitHub Stars","Workflows (3120) sorted by GitHub Stars","Workflows (2905) sorted by GitHub Stars","Workflows (3316) sorted by GitHub Stars","Workflows (4138) sorted by GitHub Stars","Workflows (3283) sorted by GitHub Stars","Workflows (2966) sorted by GitHub Stars","Workflows (3207) sorted by GitHub Stars","Workflows (3002) sorted by GitHub Stars","Workflows (3242) sorted by GitHub Stars","Workflows trending in 7 days","Workflows (5825) sorted by GitHub Stars","Workflows (3603) sorted by GitHub Stars","Workflows pushed this week","Workflows (4436) sorted by GitHub Stars","Source","Workflows (3567) sorted by GitHub Stars","Workflows trending in 14 days","Workflows (4400) sorted by GitHub Stars","Workflows (4120) sorted by GitHub Stars","Workflows (5844) sorted by GitHub Stars","Workflows (5027) sorted by GitHub Stars","Workflows (3715) sorted by GitHub Stars","Workflows (3837) sorted by GitHub Stars","Workflows (4025) sorted by GitHub Stars","Workflows (5157) sorted by GitHub Stars","Workflows (3998) sorted by GitHub Stars","Workflows (4337) sorted by GitHub Stars","Workflows (5076) sorted by GitHub Stars","Workflows (4299) sorted by GitHub Stars","Workflows (4207) sorted by GitHub Stars","Custom nodes pushed today","Custom nodes created in 7 days","Custom nodes trending in 7 days","Custom nodes pushed in 7 days","Custom nodes trending in 14 days","Custom nodes (8095) sorted by GitHub Stars","Custom nodes added to catalog today","Custom nodes trending today","Custom nodes (7817) sorted by GitHub Stars"],"sub_categories":[],"readme":"# 2026-09-25 04:10 UTC\n\nWelcome to the Awesome ComfyUI Custom Nodes list! The information in this list is fetched from both the official Comfy Registry and ComfyUI-Manager.\n\nWhether you're an AI researcher, hobbyist, or someone pushing the boundaries of generative models, these custom nodes can streamline your work. Data updated daily.\n\n## Custom nodes added to catalog today\n\n- [**MiniMax H3 Context Loop**](https://github.com/ethanfel/ComfyUI-MiniMaxH3-Context-Loop) (⭐463) *pushed 14 hours ago*: Recursive, checkpointed MiniMax H3 scene loops plus native-first AV target masking for inpainting, motion/audio continuity, audiovisual review, resume, and final assembly for ComfyUI.\n- [**GENKAI Nodes**](https://github.com/GENKAIx/Genkai-ComfyUI-Nodes) (⭐9) *pushed 6 hours ago*: PromptSync video tools, MiniMax H3 media references, prompt utilities, and video comparison nodes for ComfyUI.\n- [**MiniMax H3 Power LoRA Stack**](https://github.com/cicalooo/ComfyUI-H3-PowerLoraStack) (⭐7) *pushed 14 days ago*: Stacked multi-LoRA loader for MiniMax H3 across bf16, fp8, int8 and w4a8 weights.\n- [**ComfyUI-MiniMaxH3-Inpaint**](https://github.com/nuvulabs/ComfyUI-MiniMaxH3-Inpaint) (⭐2) *pushed a month ago*: A ComfyUI node that seeds MiniMax H3's audio-video NestedTensor latent from a plate video plus a mask, so the sampler inpaints only the masked region (object/character insertion \u0026 swap) while preserving the rest of the plate.\n- [**Camera Path**](https://github.com/phazei/ComfyUI-Camera-Path) (⭐2) *pushed an hour ago*: Reproject an image or clip through its MoGe geometry along a camera path authored in an interactive 3D editor.\n- [**SOYLAB Comfy Router**](https://github.com/soylab-edu/ComfyUI-soylab-router) (⭐2) *pushed 19 hours ago*: Run Comfy Router image, video, and audio models from one ComfyUI node with provider selection and cost references.\n- [**MiniMax H3 Frame Rate Adjustment (Ac)**](https://github.com/AharaOoO/ComfyUI-MiniMaxH3-FrameRate-Adjustment-Ac) (⭐1) *pushed a month ago*: Experimental MiniMax H3 frame-rate adjustment with temporal-coordinate retiming and pre-sampling AV duration alignment for ComfyUI.\n- [**MiniMax H3 Text Encoders**](https://github.com/kgonia/ComfyUI-MiniMaxH3TextEncoders) (⭐1) *pushed a month ago*: One ComfyUI loader for modified Qwen3-VL text encoders compatible with MiniMax-H3.\n- [**ComfyUI-MiniMaxH3-MediaPrompt**](https://github.com/YingsenP/ComfyUI-MiniMaxH3-MediaPrompt) (⭐1) *pushed a month ago*: MiniMax H3 reference media and rich prompt transport nodes for ComfyUI.\n- [**Hongs-node**](https://github.com/hong87LH/Hongs-node) (⭐1) *pushed a month ago*: Compatibility fixes and reusable workflow utility nodes for ComfyUI\n- [**Qwen Image 2.1 Fun ControlNet Union (T8)**](https://github.com/T8mars/Comfyui-Qwen-Image-2.1-Fun-Controlnet-Union-T8) (⭐1) *pushed 10 hours ago*: Native Qwen Image 2.1 Fun ControlNet Union loader and conditioning nodes for ComfyUI\n- [**Krea2 Training Free Improvements**](https://github.com/iljung1106/Krea2-Training-Free-Improvements) (⭐0) *pushed a month ago*: Composable Krea2 guidance and acceleration nodes, including GAG, NAG, Prompt Reinjection, TaylorSeer, and adaptive progressive sampling.\n- [**comfyui-gits-tracked-identity**](https://github.com/Niutonian/ComfyUI-GITS-Tracked-Identity) (⭐0) *pushed a month ago*: Temporally tracked identity graphic overlays for ComfyUI (single image, video batch, webcam)\n- [**Comfyui-DHan-Composite**](https://github.com/DHan315/Comfyui-DHan-Composite) (⭐0) *pushed 5 hours ago*: Lightweight model-agnostic compositor for preserving source regions and blending generated edits in ComfyUI.\n- [**Comfyui-DHan-InlineImage**](https://github.com/DHan315/Comfyui-DHan-InlineImage) (⭐0) *pushed 5 hours ago*: Inline image preview, transform, and mask painting node for ComfyUI.\n- [**Comfyui-DHan-Smart-Memory-Override**](https://github.com/DHan315/Comfyui-DHan-Smart-Memory-Override) (⭐0) *pushed 5 hours ago*: Manual Smart Memory control nodes for ComfyUI.\n- [**Comfyui-DHan-NanoB-Gemini**](https://github.com/DHan315/Comfyui-DHan-NanoB-Gemini) (⭐0) *pushed 20 hours ago*: Gemini / Nano Banana image generation and editing nodes for ComfyUI, derived from ComfyUI-NanoB-Edit-Gemini.\n- [**ComfyUI-ASASR**](https://github.com/claussteinmassl/ComfyUI-ASASR) (⭐0) *pushed 6 hours ago*: ASASR 4x diffusion super-resolution (FLUX.1-dev dual-LoRA) for ComfyUI, with native fp8/GGUF support. Non-commercial (CC-BY-NC-4.0 weights).\n- [**ComfyUI-MiniMaxH3RefLoRA**](https://github.com/malcolmamal/ComfyUI-MiniMaxH3RefLoRA) (⭐0) *pushed 8 hours ago*: One .safetensors holding a MiniMax H3 LoRA and its RefMod references.\n- [**Kotodama Prompt Enhancer**](https://github.com/ericmey/comfyui-kotodama) (⭐0) *pushed 7 hours ago*: Text-to-image prompt enhancer for ComfyUI using an OpenAI-compatible chat endpoint\n- [**ComfyUI-BucketCrop**](https://github.com/malcolmamal/ComfyUI-BucketCrop) (⭐0) *pushed 8 hours ago*: Crop an image to the nearest training bucket ratio, centered on a detected region.\n- [**Comfyui-DHan-Stasis**](https://github.com/DHan315/Comfyui-DHan-Stasis) (⭐0) *pushed 5 hours ago*: Keep unused ComfyUI workflow branches dormant until they are needed.\n- [**Universal Prompt Optimizer**](https://github.com/aihaipan/ComfyUI-Universal_Prompt_Optimizer) (⭐0) *pushed 18 hours ago*: Universal prompt optimizer for any ComfyUI model, with R2V bridges for both MiniMax H3 Director and TimelineDirector.\n- [**ComfyUI-APIMaster**](https://github.com/apimaster-ai/ComfyUI-APIMaster) (⭐0) *pushed 12 hours ago*: ComfyUI nodes for image and video generation through APIMaster and other OpenAI-compatible gateways. No extra Python dependencies.\n- [**ComfyUI LC Modelbuilder Nodes**](https://github.com/lonecatone23/ComfyUI_LC_ModelBuilder_nodes) (⭐0) *pushed 12 hours ago*: ComfyUI LC Modelbuilder Nodes by lonecatone23 — checkpoint/model merging tools. Starts with LC Krea2 Block Merge Advanced (per-block ratio curve + named-region sliders, reuses ComfyUI's own block-merge patching), checkpoint savers, and LC Face Variety Scorer (same-face test with InsightFace buffalo_l via onnxruntime). Companion to ComfyUI_LC123_nodes; separate Registry name.\n- [**MOSS SoundEffect v2**](https://github.com/HuizhiXu/comfyui-moss-soundeffect-v2) (⭐0) *pushed 23 hours ago*: Text-to-sound-effect nodes for MOSS-SoundEffect v2. Picks a local model and runs inference in a compatible Python, creating one beside the node when needed.\n- [**JPEG is Fine**](https://github.com/a5ah1/jpeg-is-fine) (⭐0) *pushed 21 hours ago*: A focused JPEG-saving node for ComfyUI with 4:4:4 chroma subsampling and workflow preservation\n- [**ADB Music Tools**](https://github.com/mmalexandre/comfyui-adb-music) (⭐0) *pushed 13 hours ago*: \n- [**Higgsfield API by Sherif Oneway**](https://github.com/w0ver/Higgsfield-api-comfyui-nodes) (⭐0) *pushed 11 hours ago*: Generate images and videos in ComfyUI with your own Higgsfield API credentials. Includes reference images, Seedance video generation, resumable requests, and local outputs. By Sherif Oneway.\n- [**Comfyui-DHan-MaskingADV**](https://github.com/DHan315/Comfyui-DHan-MaskingADV) (⭐0) *pushed 5 hours ago*: Advanced image masking and editing node for ComfyUI.\n\n## Custom nodes trending today\n\n- [**ComfyUI**](https://github.com/comfyanonymous/ComfyUI) (⭐134884 +133) *pushed a minute ago*: A collection of nodes for powerful and more ordered prompting. This does not /help/ you prompt better, it just helps you organize your prompting spaghetti.\n- [**MiniMax H3 Director**](https://github.com/AIMixer/ComfyUI_MiniMaxH3_Director) (⭐1970 +18) *pushed a day ago*: Multi-segment MiniMax H3 Director — official MiniMaxH3ImageToVideo / ReferenceToVideo pipeline.\n- [**ComfyUI-Manager**](https://github.com/ltdrdata/ComfyUI-Manager) (⭐16256 +13) *pushed 19 hours ago*: ComfyUI-Manager itself is also a custom node.\n- [**MiniMax H3 Activation Chunk - Star7**](https://github.com/star7code/minimax-h3-chunk-star7) (⭐58 +9) *pushed 3 days ago*: QKV/RoPE/MLP activation chunking for ComfyUI MiniMax H3 with selectable CK, SLA, Sol, and Hybrid attention paths.\n- [**ComfyUI-GGUF**](https://github.com/city96/ComfyUI-GGUF) (⭐4083 +8) *pushed 8 months ago*: GGUF Quantization support for native ComfyUI models\n- [**Krea 2 Identity Edit**](https://github.com/lbouaraba/comfyui-krea2edit) (⭐659 +8) *pushed a month ago*: Krea 2 Identity Edit — in-context instruction-edit nodes for the Krea 2 model: source-image appearance preservation (VAE reference tokens + 3D-RoPE), image-grounded instruction encoding, a reference-fidelity dial (ref_boost), and the training-matched FIT reference geometry.\n- [**Qwen-Image Photo Styles**](https://github.com/pottokao-dotcom/ComfyUI-QwenImage-PhotoStyles) (⭐11 +8) *pushed a day ago*: A prompt-rewriter node for Qwen-Image-2.1: pick a photographic style (camera language + mood) and a PE-T2I rewriter turns a short prompt into a long English one, plus a negative prompt and aspect-ratio dimensions. Not a model loader.\n- [**comfyui-klein-edit-composite**](https://github.com/supermansundies/comfyui-klein-edit-composite) (⭐116 +6) *pushed 6 months ago*: A ComfyUI node that intelligently composites a generated (AI-edited) image back onto an original image by detecting only what actually changed between the two images and blending the generated content in cleanly.\n- [**ComfyUI-PixelDriftFix**](https://github.com/Mozer/ComfyUI-PixelDriftFix) (⭐38 +6) *pushed 3 months ago*: A ComfyUI custom node designed to eliminate pixel drifting, stretching, and minor cropping inconsistencies between a source image and an edited/upscaled version.\n- [**ComfyUI-DeGrid**](https://github.com/lunaaispace-eng/ComfyUI-DeGrid) (⭐63 +6) *pushed 4 days ago*: Removes the 2px pixel grid artifact from Qwen Image VAE decoded images with auto-calibration.\n- [**ComfyUI MiniMax H3 Timeline Director**](https://github.com/Songssx/ComfyUI-MiniMaxH3-TimelineDirector) (⭐471 +6) *pushed 2 days ago*: A visual timeline and material planner for native MiniMax H3 video generation, with ordered image/video/audio references, editable Guides, prompt-planning integration, and long-video segment workflows.\n- [**VOSR 2.0**](https://github.com/ylchen333/ComfyUI-VOSR2) (⭐243 +6) *pushed 10 days ago*: ComfyUI node for VOSR 2.0 (one-step 1.4B) image super-resolution.\n- [**VNCCS - Visual Novel Character Creation Suite**](https://github.com/AHEKOT/ComfyUI_VNCCS) (⭐1608 +5) *pushed 12 days ago*: VNCCS is a comprehensive tool for creating character sprites for visual novels.\n- [**NeuralBooru**](https://github.com/ChrisJohnson89/ComfyUI-NeuralBooru) (⭐19 +5) *pushed 2 months ago*: Turn natural language into validated Danbooru tags using a local LLM\n- [**ComfyUI-FL-YuE2**](https://github.com/filliptm/ComfyUI-FL-YuE2) (⭐178 +5) *pushed a day ago*: YuE2 music generation, piano roll editing, and joint AR/NAR LoRA training for ComfyUI\n\n## Custom nodes pushed today\n\n- [**ComfyUI**](https://github.com/comfyanonymous/ComfyUI) (⭐134884) *pushed a minute ago*: A collection of nodes for powerful and more ordered prompting. This does not /help/ you prompt better, it just helps you organize your prompting spaghetti.\n- [**ComfyUI-TagForge**](https://github.com/huchukato/ComfyUI-TagForge) (⭐11) *pushed 6 minutes ago*: Tag completion with a1111-style wildcard sub-selection, CSV database support (Danbooru, e621), multiple wildcard sources, and smart parsing for professional prompt engineering in ComfyUI.\n- [**ComfyUI-OldTimeRadio**](https://github.com/jbrick2070/ComfyUI-OldTimeRadio) (⭐11) *pushed 7 minutes ago*: Press Queue once: ComfyUI writes or adapts a radio play, casts and performs it with neural voices, composes the score, and cuts a finished episode video -- all locally. No account, no API key, nothing paid. Needs an NVIDIA card with 8 GB or more, a 16 GB Apple Silicon Mac, or a CPU (start ComfyUI with --cpu), plus about 25 GB of free disk; the first run fetches roughly 12 GB of models.\n- [**TEX Wrangle**](https://github.com/xavinitram/TEX) (⭐4) *pushed 13 minutes ago*: TEX (Tensor Expression Language). Per-pixel DSL for ComfyUI\n- [**SimpleSyrup**](https://github.com/Artificial-Sweetener/SimpleSyrup) (⭐2) *pushed 24 minutes ago*: Workflow-focused ComfyUI extensions for image generation.\n- [**ComfyUI-Model-Manager-Neo**](https://github.com/rikunarita/ComfyUI-Model-Manager-Neo) (⭐1) *pushed 32 minutes ago*: Manage models: browsing, download and delete. Fork of ComfyUI-Model-Manager with improved HF/Civitai auth, huggingface_hub integration, and bug fixes.\n- [**QwenVL-Mod: Enhanced Vision-Language**](https://github.com/huchukato/ComfyUI-QwenVL-Mod) (⭐110) *pushed 33 minutes ago*: Enhanced QwenVL node with MiniMax H3 loop mode and presets, multilingual prompt generation, camera \u0026 style tag dropdowns, Pony prompt converters, Qwen 3.8 uncensored models, GGUF backend, LTX 2.3 FL2VA presets, and local model discovery for professional multimodal video workflows.\n- [**Neo Nodes**](https://github.com/neoneo-ai/ComfyUI-Neo-Nodes) (⭐1) *pushed 37 minutes ago*: ComfyUI 的 AI 提示词工作台 + Krea2 生图套件——用在线/本地大模型（支持推理/thinking 模型）一键增强、生成与反推提示词，并内置 Krea2 文生图/参考图四视图、媒体素材库与配方库，一键修复路径等便捷功能\n- [**Mochorong Nodes**](https://github.com/mochorongo/Mochorong) (⭐0) *pushed an hour ago*: Utility nodes for ComfyUI — audio gates, selectors, conditional routing, and type conversion.\n- [**ComfyUI LC123 Nodes**](https://github.com/lonecatone23/ComfyUI_LC123_nodes) (⭐22) *pushed an hour ago*: ComfyUI LC123 Nodes by lonecatone23 — Image Label, Skin Upscale, Bypass Relay, Image/Mask Pass, Widget To String, Save Image + Metadata, Any Empty Bool/Int/Float, Int Split, LC Batch Image, Tone Match, Color Match mask, MiniMax H3 pipe, Image-Mask Resize, LC Lighting Control, Photo Style, Skin Beauty, Sharpen Pro, prompt builder, sampler configure, Sigma Curve, Sigma Resample, image FX, pipes, notify.\n- [**Camera Path**](https://github.com/phazei/ComfyUI-Camera-Path) (⭐2) *pushed an hour ago*: Reproject an image or clip through its MoGe geometry along a camera path authored in an interactive 3D editor.\n- [**WextraUI**](https://github.com/sickbraintwo/WextraUI) (⭐0) *pushed an hour ago*: Extra nodes for ComfyUI, from the Winteraction workbench. Time works for you: WextraUI nodes have a control after generate and the carry that links them, so a queue of runs changes checkpoint, LoRA, sampler, scheduler, seed, frame and prompt on its own, and WSave Image puts every image in the right place with a file name built from parts. One press of Run and the machine never stops. Twenty nodes: WCheckpoint, WLoRA, WSampler, WScheduler, WInt, WFloat, WSwitch, WRoute, WDifference, WFrame, WPrompt Rows and the WScene / WLoop family for MiniMax H3.\n- [**ComfyUI-Prompt-Manager**](https://github.com/FranckyB/ComfyUI-Prompt-Manager) (⭐157) *pushed an hour ago*: A simple custom node for ComfyUI that allows you to save and reuse prompts, organized into different categories\n- [**CometAPI**](https://github.com/jieg9341-lab/ComfyUI-CometAPI) (⭐17) *pushed an hour ago*: A multimodal API workflow toolkit for ComfyUI with image, video, audio, text, batch generation, asset cards, and an integrated chat assistant.\n- [**rgthree's ComfyUI Nodes**](https://github.com/rgthree/rgthree-comfy) (⭐3496) *pushed an hour ago*: Nodes: Seed, Reroute, Context, Lora Loader Stack, Context Switch, Fast Muter. These custom nodes helps organize the building of complex workflows.\n- [**Pruna nodes for ComfyUI**](https://github.com/PrunaAI/ComfyUI_pruna) (⭐66) *pushed an hour ago*: This repository explains how to accelerate image generation in ComfyUI using Pruna, an inference optimization engine that makes AI models faster, smaller, cheaper, and greener. ComfyUI is a popular node-based GUI for image generation models, for which we provide a custom compilation node that accelerates Stable Diffusion (SD) and Flux inference, while preserving output quality.\n- [**WeiLin-Comfyui-Tools**](https://github.com/weilin9999/WeiLin-Comfyui-Tools) (⭐536) *pushed an hour ago*: quickly use the prompt word tool in ComfyUI\n- [**VRGameDevGirl Video Enhancement Nodes**](https://github.com/vrgamegirl19/comfyui-vrgamedevgirl) (⭐733) *pushed an hour ago*: Film grain and color match nodes designed for high-quality frame-by-frame video enhancement in ComfyUI.\n- [**ComfyUI-RIFE-TensorRT-Auto**](https://github.com/huchukato/ComfyUI-RIFE-TensorRT-Auto) (⭐6) *pushed an hour ago*: Ultra fast video frame interpolation for ComfyUI using RIFE with TensorRT acceleration. Auto-detects CUDA version, installs matching TensorRT wheels, and downloads RIFE models automatically.\n- [**ComfyUI-Upscaler-TensorRT-Auto**](https://github.com/huchukato/ComfyUI-Upscaler-TensorRT-Auto) (⭐2) *pushed an hour ago*: Fast image upscaling for ComfyUI using TensorRT acceleration (2-4x faster than standard methods). Auto-detects CUDA version and installs matching TensorRT wheels. Supports multiple upscaling models with automatic engine building and optimized inference for NVIDIA GPUs.\n- [**ComfyUI-HuggingFace**](https://github.com/huchukato/ComfyUI-HuggingFace) (⭐8) *pushed an hour ago*: HuggingFace model downloader for ComfyUI — search, download, and organize AI models directly within your workflow with integrated Civitai repository access and batch download support.\n- [**Perfect Video Resolution**](https://github.com/huchukato/ComfyUI-PerfectVideoResolution) (⭐5) *pushed an hour ago*: Automatically calculates and applies the optimal resolution for Wan 2.2, MiniMax H3, and LTX video generation models based on aspect ratio and model requirements.\n- [**ComfyUI-Xz3r0-Nodes**](https://github.com/Xz3r0-M/ComfyUI-Xz3r0-Nodes) (⭐14) *pushed 2 hours ago*: Custom ComfyUI nodes: XMath, XResolution, XImageSave, XLatentLoad, XLatentSave, XVideoSave, XAudioSave, XStringGroup, XWorkflowSave, XMetadataWorkflow(Extension), XDateTimeString, XFitView(Extension) ...and more\n- [**H3 Project Suite**](https://github.com/Adudeguyman/ComfyUI-H3-Project-Suite) (⭐38) *pushed 2 hours ago*: Long-form video with MiniMax H3. Chain clips that genuinely continue each other in picture and sound, managed as a project with review, takes, branching and one-click export. Each clip is handed to the next in latent space, so no decode and re-encode round trip sits between them.\n- [**LanPaint**](https://github.com/scraed/LanPaint) (⭐1404) *pushed 2 hours ago*: Achieve seamless inpainting results without needing a specialized inpainting model.\n- [**ComfyUI-RPG-Characters**](https://github.com/lord-lethris/ComfyUI-RPG-Characters) (⭐7) *pushed 2 hours ago*: Stylized RPG character prompt generator for ComfyUI. Supports standard and Ollama-based prompts, works with SD, SDXL, Flux, and more.\n- [**FastVideo**](https://github.com/hao-ai-lab/FastVideo) (⭐4501) *pushed 2 hours ago*: A custom node suite for ComfyUI that provides accelerated multi-GPU video generation using [a/FastVideo](https://github.com/hao-ai-lab/FastVideo).\n- [**MiniMax H3 Flow-Aligned Regenerate**](https://github.com/xmarre/MiniMax-H3-Flow-Aligned-Regenerate) (⭐16) *pushed 3 hours ago*: H3-native flow-aligned and progressive-resolution regeneration for ComfyUI\n- [**ComfyUI-mnemic-nodes**](https://github.com/MNeMoNiCuZ/ComfyUI-mnemic-nodes) (⭐105) *pushed 3 hours ago*: Added Lora Loader - Tag node, originally by badjeff\n- [**ComfyUI Eclipse**](https://github.com/r-vage/ComfyUI_Eclipse) (⭐36) *pushed 3 hours ago*: Comprehensive ComfyUI custom node suite featuring Smart Prompt with wildcards, a pipe ecosystem, universal type converters, image/video utilities, and workflow helpers. V3 API, Nodes 2.0 compatible.\n- [**ComfyUI LC MaskMaker Nodes**](https://github.com/lonecatone23/ComfyUI_LC_MaskMaker_nodes) (⭐0) *pushed 4 hours ago*: ComfyUI LC MaskMaker Nodes by lonecatone23: on-node Outpaint and Create Mask, background removal, Segment Anything, person masks, mask refine, image blend, auto adjust, depth and normal maps. Models load on demand and are labelled with their licenses. Companion to ComfyUI_LC123_nodes; separate Registry name.\n- [**comfyui_AcademiaSD**](https://github.com/AcademiaSD/comfyui_AcademiaSD) (⭐80) *pushed 4 hours ago*: Official set of custom nodes of AcademiaSD.\n- [**PixelOE**](https://github.com/KohakuBlueleaf/PixelOE) (⭐506) *pushed 5 hours ago*: Detail-Oriented Pixelization based on Contrast-Aware Outline Expansion.\n- [**Comfyui-DHan-Stasis**](https://github.com/DHan315/Comfyui-DHan-Stasis) (⭐0) *pushed 5 hours ago*: Keep unused ComfyUI workflow branches dormant until they are needed.\n- [**Comfyui-DHan-Smart-Memory-Override**](https://github.com/DHan315/Comfyui-DHan-Smart-Memory-Override) (⭐0) *pushed 5 hours ago*: Manual Smart Memory control nodes for ComfyUI.\n- [**Comfyui-DHan-InlineImage**](https://github.com/DHan315/Comfyui-DHan-InlineImage) (⭐0) *pushed 5 hours ago*: Inline image preview, transform, and mask painting node for ComfyUI.\n- [**Comfyui-DHan-MaskingADV**](https://github.com/DHan315/Comfyui-DHan-MaskingADV) (⭐0) *pushed 5 hours ago*: Advanced image masking and editing node for ComfyUI.\n- [**Comfyui-DHan-Composite**](https://github.com/DHan315/Comfyui-DHan-Composite) (⭐0) *pushed 5 hours ago*: Lightweight model-agnostic compositor for preserving source regions and blending generated edits in ComfyUI.\n- [**KIE.ai Nodes Next**](https://github.com/felipederosilva/ComfyUI-KIE-Nodes-Next) (⭐0) *pushed 5 hours ago*: Individual KIE.ai model nodes for ComfyUI with live catalog sync, one-time credentials, and native media I/O.\n- [**ComfyUI-IntoTheLatent-Utils**](https://github.com/Into-The-Latent/ComfyUI-IntoTheLatent-Utils) (⭐2) *pushed 6 hours ago*: ComfyUI utility nodes by Into The Latent.\n- [**RandomLoRALoader**](https://github.com/shin131002/RandomLoRALoader) (⭐2) *pushed 6 hours ago*: A ComfyUI custom node for randomly selecting and applying LoRAs from multiple folders with support for trigger words, sample prompts, and strength randomization.\n- [**ComfyUI-SongLRC**](https://github.com/TheAwaken1/ComfyUI-SongLRC) (⭐4) *pushed 6 hours ago*: Timed .lrc lyrics for generated songs, saved beside the audio, with a player that highlights each line as it is sung.\n- [**GENKAI Nodes**](https://github.com/GENKAIx/Genkai-ComfyUI-Nodes) (⭐9) *pushed 6 hours ago*: PromptSync video tools, MiniMax H3 media references, prompt utilities, and video comparison nodes for ComfyUI.\n- [**ComfyUI Anima Remap**](https://github.com/shin131002/ComfyUI-Anima-Remap) (⭐10) *pushed 6 hours ago*: Use LoRAs, model merges and ControlNets (LLLite/VACE) across Anima generations (Anima, 2.9B, 3.8B/Pro52 and beyond) with automatic block-index remapping\n- [**ComfyUI-ASASR**](https://github.com/claussteinmassl/ComfyUI-ASASR) (⭐0) *pushed 6 hours ago*: ASASR 4x diffusion super-resolution (FLUX.1-dev dual-LoRA) for ComfyUI, with native fp8/GGUF support. Non-commercial (CC-BY-NC-4.0 weights).\n- [**Anymatix**](https://github.com/Anymatix/anymatix-comfy-nodes) (⭐0) *pushed 6 hours ago*: The nodes Anymatix runs on: URL-addressed model loaders that download what a workflow asks for, plus CLIPSeg, masking, SAM2 coordinates and the save nodes Anymatix reads its results from.\n- [**comfyui-Karga_RemoteWorkflows**](https://github.com/kapakahi/comfyui-Karga_RemoteWorkflows) (⭐0) *pushed 7 hours ago*: A standalone ComfyUI custom node that sends workflows to a remote ComfyUI instance and returns the output image — all in a single node.\n- [**AusBoss**](https://github.com/ausboss/ComfyUI-AusBoss) (⭐2) *pushed 7 hours ago*: Image and video nodes with compact controls: Image and Video Crop + Rotate + Pad (frame or clip), Load Image + Pad, Image Resize, Align Image, Image Size, Color Match, Image Compare A/B, Save Image (PNG, lossless WebP/JXL, exact names, captions), Load Video, Save Video, Select Frame, Frame Interpolate, Mask Refine, LaMa Inpaint, Crop For Inpaint, Stitch Inpaint, LoRA Loader, Krea 2 Encode and Outpaint Model Patch, Resolution Master, Seed, Select Every Nth, Split Batch, Merge Batches, Text, Integer, Float, Math Expression, Show Text, Free Memory, Workflow Note, and Run Timer. Example workflows for Qwen Image 2.1, Krea 2, Klein 9B, LTX 2.3 and MiniMax H3.\n- [**AlekPet/ComfyUI_Custom_Nodes_AlekPet**](https://github.com/AlekPet/ComfyUI_Custom_Nodes_AlekPet) (⭐1527) *pushed 7 hours ago*: Nodes: PoseNode, PainterNode, TranslateTextNode, TranslateCLIPTextEncodeNode, DeepTranslatorTextNode, DeepTranslatorCLIPTextEncodeNode, ArgosTranslateTextNode, ArgosTranslateCLIPTextEncodeNode, PreviewTextNode, HexToHueNode, ColorsCorrectNode, IDENode.\n- [**ComfyUI Complex Prompt Nodes**](https://github.com/ArtemKo7v/ComfyUI-Complex-Prompt) (⭐1) *pushed 7 hours ago*: ComfyUI node for working with complex prompts with support for variables, randomness, and basic logic.\n- [**Pixar's OpenUSD**](https://github.com/cjhosken/ComfyUI-OpenUSD) (⭐10) *pushed 7 hours ago*: Pixar's OpenUSD pipeline integration for ComfyUI. Natively compose and render 3D scenes within your node workflows.\n- [**ComfyUI-MiniMax-H3-Extend**](https://github.com/kat3ri/ComfyUI-MiniMax-H3-Extend) (⭐28) *pushed 7 hours ago*: Adds video continuation / extension capabilities to Minimax-H3 in ComfyUI\n- [**ComfyUI Sol-H3**](https://github.com/xmarre/ComfyUI-Sol-H3) (⭐41) *pushed 7 hours ago*: Native ComfyUI MiniMax-H3 exact runtime and composable Sana Sol-Attn integration\n- [**BrainDead Nodes**](https://github.com/BizaNator/ComfyUI-BrainDead) (⭐15) *pushed 7 hours ago*: Comprehensive ComfyUI nodes for 3D mesh processing, PBR texture baking, caching, character consistency, and prompt iteration\n- [**comfyui-immich**](https://github.com/ericmey/comfyui-immich) (⭐2) *pushed 7 hours ago*: ComfyUI custom nodes for Immich integration — upload, metadata, album management\n- [**Kotodama Prompt Enhancer**](https://github.com/ericmey/comfyui-kotodama) (⭐0) *pushed 7 hours ago*: Text-to-image prompt enhancer for ComfyUI using an OpenAI-compatible chat endpoint\n- [**ComfyUI-WepeNerd**](https://github.com/WepeNerd/ComfyUI-WepeNerd) (⭐4) *pushed 8 hours ago*: Custom node pack featuring an interactive visual resolution picker and resolution suggestion tool with real-time dimension readout and divisor snapping. (Description by CC)\n- [**ComfyUI-BucketCrop**](https://github.com/malcolmamal/ComfyUI-BucketCrop) (⭐0) *pushed 8 hours ago*: Crop an image to the nearest training bucket ratio, centered on a detected region.\n- [**YuE2 Music**](https://github.com/pytraveler/YuE2-ComfyUI) (⭐52) *pushed 8 hours ago*: ComfyUI nodes for YuE2-3B: a style description and lyrics become a readable score and then a complete 48 kHz stereo song, generated locally.\n- [**ComfyUI LC Vision Nodes**](https://github.com/lonecatone23/ComfyUI_LC_Vision_nodes) (⭐3) *pushed 8 hours ago*: ComfyUI LC Vision Nodes by lonecatone23 — a Qwen-VL GGUF vision/captioning pack built to actually survive shared-VRAM ComfyUI workflows: a Loader + Run split (so the model stays resident instead of being torn down every call), multi-reference input (several independent images plus a video in one call, not just a single batched slot), and an install script that resolves a matching llama-cpp-python vision wheel for the user's own machine instead of pointing at a manual wheel-matching guide. Companion to ComfyUI_LC123_nodes; separate Registry name.\n- [**ComfyUI-MiniMaxH3RefLoRA**](https://github.com/malcolmamal/ComfyUI-MiniMaxH3RefLoRA) (⭐0) *pushed 8 hours ago*: One .safetensors holding a MiniMax H3 LoRA and its RefMod references.\n- [**BudgetPixel**](https://github.com/budgetpixel-ai/comfyui-budgetpixel) (⭐4) *pushed 8 hours ago*: Official BudgetPixel nodes for ComfyUI — generate images, video, music and sound effects with 60+ hosted models (FLUX, Seedream, Kling, Seedance, Wan, and more) using your BudgetPixel API key.\n- [**SceneWeaver**](https://github.com/EnragedAntelope/comfyui-sceneweaver) (⭐3) *pushed 9 hours ago*: One click, one whole coherent scene: the place, what is standing in it, and what it is doing - written as prose a text encoder can follow, where every detail agrees with every other one. A multi-genre scene engine: sci-fi (alien creatures, spacefarers, mechs, starships, stations, wrecks, worlds) fantasy (dragons, mythic beasts, giants, goblins, centaurs, elves, undead, golems, castles, airships) and horror (ghouls, vampires, banshees, cryptids, eldritch horrors, cultists, cursed objects, haunted houses, with a gore filter that starts on No gore), each drawn across a full morphology, with entities that wire across genres. Every field independently lockable.\n- [**ComfyUI ARG Toolkit**](https://github.com/AzelusLightvale/ComfyUI-ARG-Toolkit) (⭐1) *pushed 9 hours ago*: A collection of ComfyUI nodes for cryptography, steganography, encryption, decryption, and tools needed to both make and solve ARGs (Alternative Reality Games) and secret messages.\n- [**comfyui-svdint4**](https://github.com/wjie98/comfyui-svdint4) (⭐3) *pushed 9 hours ago*: ComfyUI custom node for loading SVDInt4-quantized Wan/Bernini DiT models.\n- [**Continuity**](https://github.com/roadmaus/ComfyUI-Continuity) (⭐94) *pushed 9 hours ago*: One node for AI video and stills across seven model families: MiniMax H3, LTX 2.5, Krea 2, Ideogram 4.0, Qwen Image Edit, Flux 2 Klein and Qwen Image 2.1. Write a prompt, attach media with @, press Render. Everything renders locally from open weights. The optional prompt refiner can run in-process or on your own server or API provider.\n- [**MiniMax Creator**](https://github.com/roadmaus/ComfyUI-MiniMax-Creator) (⭐94) *pushed 9 hours ago*: One node for MiniMax H3 video, one shot or twenty: write a sentence, attach media with @, press Run — get a finished clip with sound. Local open weights only, no API key.\n- [**DemonAlone-JS_Addon-ComfyUI**](https://github.com/DemonAlone/DemonAlone-JS_Addon-ComfyUI) (⭐1) *pushed 9 hours ago*: Interactive JavaScript nodes: Load Video with real-time preview, Video Maker (image batch to MP4), plus upcoming queue management and dynamic UI tools. Enhances workflow flexibility.\n- [**comfyui-OreX**](https://github.com/orex2121/comfyui-OreX) (⭐44) *pushed 9 hours ago*: comfyui-OreX is a set of nodes for using LLM models via a free API.\n- [**H3 LongTake**](https://github.com/mark9009/ComfyUI-H3-LongTake) (⭐23) *pushed 9 hours ago*: Long MiniMax H3 videos clip by clip with continuity: motion/identity transfer (Ref2VA) and style transfer / retexture (guide latent + StyleTransfer LoRA), resumable, one clip in VRAM at a time.\n- [**raylight**](https://github.com/komikndr/raylight) (⭐444) *pushed 9 hours ago*: Enable tensor split multi gpu capability in Comfy UI\n- [**ComfyUI-H3-upgrade-kit**](https://github.com/flywhale-666/ComfyUI-H3-upgrade-kit) (⭐3) *pushed 9 hours ago*: MiniMax H3 semantic conditioning, audio frame-rate sync, latent upscaling, tiled sampling, batched VAE decoding, motion continuation and SelfLift sampling.\n- [**ComfyUI-LTXVideo**](https://github.com/Lightricks/ComfyUI-LTXVideo) (⭐4142) *pushed 9 hours ago*: Custom nodes for LTX-Video support in ComfyUI\n- [**ComfyUI CoolB Nodes**](https://github.com/CoolBreeze164/ComfyUI-CoolB-Nodes) (⭐0) *pushed 10 hours ago*: A simple pack of utility nodes for ComfyUI featuring saving/loading speakers with transcripts (useful alongside TTS packs), execution flow control (muting/bypassing nodes and groups on trigger to actively change the workflow state from run to run), some useful text file utilities (including save/load text file) and data type conversion.\n- [**Frontend Cleanup Node**](https://github.com/brucew4yn3rp/ComfyUI_FrontEndCleanup) (⭐2) *pushed 10 hours ago*: This node customizes the ComfyUI frontend by relocating the action bar into the top bar and hiding selected UI elements to reduce visual clutter.\n- [**ComfyUI-Pixaroma**](https://github.com/pixaroma/ComfyUI-Pixaroma) (⭐403) *pushed 10 hours ago*: Creative suite for ComfyUI: fullscreen Image Composer, Paint, 3D Builder, Image Crop and AudioReact editors, plus Load/Save Image, Save Mp4, Load Video, Inpaint Crop and Stitch, Outpaint, XY Plot, Prompt library, LoRA Loader, Control Panel, Notes, Labels, and canvas tools for aligning and grouping nodes.\n- [**Modal Bridge — 云端 GPU 跑图 / Cloud GPU**](https://github.com/lynclee/comfyui_modal_bridge) (⭐6) *pushed 10 hours ago*: 一键把当前 ComfyUI 工作流推到 Modal Serverless GPU(H100)跑,自动同步本地模型/自定义节点,出图回填画板,零终端。 | One-click run the current ComfyUI workflow on Modal Serverless GPU (H100); auto-sync local models/custom-nodes, results back to the canvas, no terminal.\n- [**comfyui-obvpm**](https://github.com/chanon/comfyui-obvpm) (⭐54) *pushed 10 hours ago*: Bundle multiple wires into one wire. Create customizable Presets nodes. Compose ref images in one node. ComfyUI nodes to save time and keep your workflows tidy.\n- [**Qwen Image 2.1 Fun ControlNet Union (T8)**](https://github.com/T8mars/Comfyui-Qwen-Image-2.1-Fun-Controlnet-Union-T8) (⭐1) *pushed 10 hours ago*: Native Qwen Image 2.1 Fun ControlNet Union loader and conditioning nodes for ComfyUI\n- [**Higgsfield API by Sherif Oneway**](https://github.com/w0ver/Higgsfield-api-comfyui-nodes) (⭐0) *pushed 11 hours ago*: Generate images and videos in ComfyUI with your own Higgsfield API credentials. Includes reference images, Seedance video generation, resumable requests, and local outputs. By Sherif Oneway.\n- [**H3 Optimizations**](https://github.com/Zironic/H3-Optimizations) (⭐116) *pushed 11 hours ago*: Production sparse attention, token ordering, and memory optimization nodes for MiniMax H3 in ComfyUI\n- [**Image MetaHub Save Node**](https://github.com/LuqP2/ImageMetaHub-ComfyUI-Save) (⭐16) *pushed 11 hours ago*: Official companion node for Image MetaHub. Saves A1111/Civitai-compatible parameters plus extended Image MetaHub metadata (workflow JSON, SHA256 model hashes, VRAM peak/total, GPU device, generation time, and steps/sec) for reproducibility and benchmarking.\n- [**ComfyUI_StarNodes**](https://github.com/Starnodes2024/ComfyUI_StarNodes) (⭐106) *pushed 11 hours ago*: NODES: StarNode Startsettings for Flux and SD, Smplers for Flux and SD, Detail Deamon, Wildcards and more Helper Nodes\n- [**DDRK Omega Sampler**](https://github.com/HVOSTOVSKY/DDRK-Omega-Sampler) (⭐0) *pushed 11 hours ago*: One-click universal sampler for ComfyUI: Flow Matching + EDM, the HC3 integrator (third order at one model call per step, self-damping at high CFG), automatic per-model settings\n- [**Qwen Image 2.1 Prompt Rewrite T8**](https://github.com/T8mars/Comfyui-Qwen-Image-Prompt-Rewrite-T8) (⭐30) *pushed 12 hours ago*: Local Qwen Image 2.1 prompt rewriting for text-to-image and 1-10 image editing in ComfyUI\n- [**ComfyUI LC Modelbuilder Nodes**](https://github.com/lonecatone23/ComfyUI_LC_ModelBuilder_nodes) (⭐0) *pushed 12 hours ago*: ComfyUI LC Modelbuilder Nodes by lonecatone23 — checkpoint/model merging tools. Starts with LC Krea2 Block Merge Advanced (per-block ratio curve + named-region sliders, reuses ComfyUI's own block-merge patching), checkpoint savers, and LC Face Variety Scorer (same-face test with InsightFace buffalo_l via onnxruntime). Companion to ComfyUI_LC123_nodes; separate Registry name.\n- [**ComfyUI-APIMaster**](https://github.com/apimaster-ai/ComfyUI-APIMaster) (⭐0) *pushed 12 hours ago*: ComfyUI nodes for image and video generation through APIMaster and other OpenAI-compatible gateways. No extra Python dependencies.\n- [**Qwen-Image 2.1 Prompt Enhancer (MTP)**](https://github.com/mozophe/ComfyUI-Qwen-Image-2.1-PromptEnhancer-MTP) (⭐1) *pushed 12 hours ago*: ComfyUI nodes for Qwen-Image 2.1's official prompt enhancer, with MTP speculative decoding for faster generation.\n- [**ComfyUI-Przewodo-Utils**](https://github.com/przewodo/ComfyUI-Przewodo-Utils) (⭐4) *pushed 13 hours ago*: Utilities to make it easy to develop advanced Workflows without having to use a lot of nodes for simple stuff.\n- [**ComfyUI-NTX-support-nodes**](https://github.com/nekotxt/ComfyUI-NTX-support-nodes) (⭐0) *pushed 13 hours ago*: Nodes to support the creation of pipes, and other utilities\n- [**ComfyUI-ImageViewer**](https://github.com/szprivate/ComfyUI-ImageViewer) (⭐1) *pushed 13 hours ago*: The bEpic image viewer by sebastianzilius is a professional floating image viewer for ComfyUI - multi-tab, history snapshots, side-by-side comparison, playback timeline, exposure/channel controls, and a live parameter panel.\n- [**Zen Image Edit T8**](https://github.com/T8mars/comfyui-Zen-Image-Edit-T8) (⭐1) *pushed 13 hours ago*: Native ComfyUI nodes for Zen Image Edit with a single-file Qwen-Image-2.1 checkpoint and student text encoder.\n- [**ADB Music Tools**](https://github.com/mmalexandre/comfyui-adb-music) (⭐0) *pushed 13 hours ago*: \n- [**ComfyUI-Utility-Suite**](https://github.com/tom-m-2020/ComfyUI-Utility-Suite) (⭐0) *pushed 13 hours ago*: \n- [**ComfyUI-Pollinations-BYOP**](https://github.com/ChunkyPanda29/ComfyUI-Pollinations-BYOP) (⭐4) *pushed 14 hours ago*: Premium Quad-Modal suite (Image, Video, Text, Audio) for Pollinations.ai. Includes native Settings menu integration, BYOP support, and an automated real-time model list updater.\n- [**ComfyUI-OTP-Auth**](https://github.com/ah-kun/ComfyUI-OTP-Auth) (⭐4) *pushed 14 hours ago*: Adds simple One-Time Password (OTP) authentication using Google Authenticator to protect publicly accessible ComfyUI instances.\n- [**ComfyUI Prompt Workbench**](https://github.com/matsukasa/ComfyUI-Prompt-Workbench) (⭐2) *pushed 14 hours ago*: タグ選択、翻訳、編集、整理をまとめて扱うComfyUI向けプロンプト作業台 / A structured prompt workbench for ComfyUI with tag browsing, translation, editing, and organization.\n- [**二次元角色选择器 / Anime Character Selector**](https://github.com/R0smontis/comfyui_anime_character_selector) (⭐0) *pushed 14 hours ago*: 面向 WAI Illustrious 的二次元角色选择器,提供中文角色名和英文模型标签下拉列表。\n- [**Muse Minimax Director V1.2**](https://github.com/muse-collective-26/MiniMaxH3-Director-V1.2) (⭐42) *pushed 14 hours ago*: Timeline-based director node for MiniMax H3 — visual CUT/segment editor, multi-character reference images, reference video + reference audio (with per-clip audio pairing for lipsync/voice reference), First/Last Frame mode, automatic chunking, two-stage sampling, a VAE re-encode continuity mode that hard-freezes a real re-encoded window of the previous chunk's output across the chunk boundary, and an explicit Seed Hunt on/off switch with a 1-4 candidate count. Bundled with its companion Muse Minimax Refine node — picks one Seed Hunt candidate and continues its sigma schedule at a higher resolution, including full multi-chunk Latent-Only Scouting candidates, not just a single chunk.\n- [**MiniMax H3 Contex Loop**](https://github.com/ethanfel/ComfyUI-MiniMaxH3-Contex-Loop) (⭐463) *pushed 14 hours ago*: Recursive MiniMax H3 scene loops with motion and audio continuity, visual planning, review gates, atomic checkpoints, resume, and final video assembly.\n- [**MiniMax H3 Context Loop**](https://github.com/ethanfel/ComfyUI-MiniMaxH3-Context-Loop) (⭐463) *pushed 14 hours ago*: Recursive, checkpointed MiniMax H3 scene loops plus native-first AV target masking for inpainting, motion/audio continuity, audiovisual review, resume, and final assembly for ComfyUI.\n- [**ComfyUI-Apt_Preset**](https://github.com/cardenluo/ComfyUI-Apt_Preset) (⭐339) *pushed 15 hours ago*: ComfyUI Preset Manager, supporting various preset templates and workflow management\n- [**ComfyUI-Koolook**](https://github.com/malkuthro/ComfyUI-Koolook) (⭐8) *pushed 15 hours ago*: This repository provides custom nodes for ComfyUI tailored for VFX and AI image/video generation workflows\n- [**ComfyUI-PainterNodes**](https://github.com/princepainter/ComfyUI-PainterNodes) (⭐194) *pushed 15 hours ago*: Video generation nodes for LTX, Wan2.2, Bernini, qwen image edit,flux image edit, and utility nodes.\n- [**Sagado Nodes for ComfyUI**](https://github.com/5agado/ComfyUI-Sagado-Nodes) (⭐1) *pushed 15 hours ago*: NODES: Image Loader, Get Num Frames, Get Resolution Node, Video Loader, Film Grain\n- [**Y7Nodes for ComfyUI**](https://github.com/yushan777/ComfyUI-Y7Nodes) (⭐8) *pushed 16 hours ago*: A collection of utility / quality-of-life nodes for ComfyUI. Probably only useful to me.\n- [**comfyui-obvpm-timeline**](https://github.com/chanon/comfyui-obvpm-timeline) (⭐35) *pushed 16 hours ago*: A timeline for MiniMax H3 video: generate a clip, then extend it, prepend to it or bridge between clips seamlessly from their saved latents. The Timeline node is a mini video editor to arrange, cut and preview them, make seamless loops, and upscale the whole sequence in one pass. Companion to comfyui-obvpm.\n- [**ComfyUI-LLM-Session**](https://github.com/kantan-kanto/ComfyUI-LLM-Session) (⭐35) *pushed 16 hours ago*: Local LLM session nodes for ComfyUI using GGUF and llama.cpp, supporting Llama, Mistral, Qwen, DeepSeek, GLM, Gemma, Phi, LLaVA and gpt-oss, enabling both user–model chat and model-to-model dialogue without external runtimes like Ollama.\n- [**JosiaNodes**](https://github.com/Josia-doit/ComfyUI_JosiaNodes) (⭐18) *pushed 17 hours ago*: 一套功能完整、轻量稳定的 ComfyUI 实用节点集，共十七类节点：模型加载（多合一）、多图加载（批量上传/拖拽/粘贴，逐图等比缩放）、文本编码（文生图/图生图/参考Latent一体化）、风格选择（内置 Krea2 风格库）、图像缩放裁切（选择比例+3种自定义模式）、LoRA堆叠（1-10组顺序应用）、分组控制、图像对比、流量阀门、随机种子、缓存清理、文本列表、文本保存、媒体保存（图像/视频/音频/潜空间全能落地，自带VAE解码）、加载Latent（读取.latent单独解码）。另附编组增强画布补丁与模型列表增强。全中文界面，原生控件，不依赖第三方库。\n- [**Apex Artist - Image Resize**](https://github.com/ApexArtist/comfyui-apex-artist) (⭐5) *pushed 17 hours ago*: Professional image resizing node with 6 advanced algorithms, intelligent aspect ratio handling, crop/pad options, and batch processing support. Perfect for AI workflows, photography, and digital art.\n- [**Neons Style Explorer**](https://github.com/Neon-Sparks/ComfyUI-NeonsStyleExplorer) (⭐22) *pushed 17 hours ago*: Neons Style Explorer — a hand-written style-prefix catalog for ComfyUI, in natural language or booru tags, with a preview gallery.\n- [**ComfyUI-RookieUI**](https://github.com/rookiestar28/ComfyUI-RookieUI) (⭐92) *pushed 17 hours ago*: The ultimate A1111-style sidebar. Bring the classic UX you know and love into ComfyUI.\n- [**ComfyUI_RaykoStudio**](https://github.com/Raykosan/ComfyUI_RaykoStudio) (⭐82) *pushed 17 hours ago*: A node for ComfyUI that allows you to overlay text on an image in an area defined by a mask, with support for text rotation, custom fonts, line breaks and transparency.\n- [**Wild H3C — MiniMax H3 for Apple Silicon**](https://github.com/skaiy/wild-h3c-comfyui) (⭐1) *pushed 17 hours ago*: MiniMax H3 video generation on Apple Silicon, powered by the h3.c Metal engine.\n- [**ComfyUI Timesaver Nodes**](https://github.com/AlexYez/comfyui-timesaver) (⭐13) *pushed 17 hours ago*: ComfyUI nodes from [Timesaver](https://github.com/AlexYez/comfyui-timesaver).\n- [**ComfyUI-UtilsCollection**](https://github.com/silveroxides/ComfyUI-UtilsCollection) (⭐40) *pushed 17 hours ago*: Utilities making it easy to set up inference parameters.\n- [**DemonAlone-nodes-ComfyUI**](https://github.com/DemonAlone/DemonAlone-nodes-ComfyUI) (⭐4) *pushed 18 hours ago*: A collection of nodes that provide dynamic dropdown selectors for Samplers, Schedulers, Checkpoints, and Diffusion Models, outputting a comma-separated string for use in XY plots.\n- [**FxAi(凤希全能节点)**](https://github.com/fxai666/fxai-toolkit) (⭐42) *pushed 18 hours ago*: 音视频、图片、提示词多资源批量管理器，无限分镜流、无限长视频流、无限循环流必备，如需帮助请进Q群：775649071\n- [**Universal Prompt Optimizer**](https://github.com/aihaipan/ComfyUI-Universal_Prompt_Optimizer) (⭐0) *pushed 18 hours ago*: Universal prompt optimizer for any ComfyUI model, with R2V bridges for both MiniMax H3 Director and TimelineDirector.\n- [**Danbooru Tag JP Assist**](https://github.com/ukr8b3g-cmyk/Danbooru-Tag-JP-Assist) (⭐3) *pushed 18 hours ago*: Japanese-assisted tag autocomplete for ComfyUI text areas. Supports Danbooru tags, bundled natural language tags, local CSV tag files, Japanese aliases, popup settings, and optional Danbooru CSV update from Hugging Face.\n- [**ComfyUI-BCNodes**](https://github.com/0xBeycan/ComfyUI-BCNodes) (⭐0) *pushed 18 hours ago*: Utility nodes for ComfyUI: logic, mask, image, PostFx film looks, dataset analysis (Caption Audit, Image Quality Gate), Social Media Export, SeedVR2 streaming, loaders and workflow helpers (AutoBypass, Anything Everywhere, comparers).\n- [**Comfyui_Fd_Nodes**](https://github.com/Xyc2016/Comfyui_Fd_Nodes) (⭐0) *pushed 18 hours ago*: Custom nodes for fd project\n- [**Minimalistic Comfy Wrapper WebUI**](https://github.com/light-and-ray/Minimalistic-Comfy-Wrapper-WebUI) (⭐139) *pushed 18 hours ago*: Additional UI focused on inference. Stable UI states; presets; and advanced queue. Based on Gradio\n- [**ComfyUI-Arisu-Nodes**](https://github.com/swqa7697/ComfyUI-Arisu-Nodes) (⭐8) *pushed 19 hours ago*: A package of useful ComfyUI nodes optimizing user experience.\n- [**ComfyUI-Manager**](https://github.com/ltdrdata/ComfyUI-Manager) (⭐16256) *pushed 19 hours ago*: ComfyUI-Manager itself is also a custom node.\n- [**ComfyUI-Workflow-Studio**](https://github.com/ketle-man/ComfyUI-Workflow-Studio) (⭐14) *pushed 19 hours ago*: Workflow management and generation UI plugin. Browse, organize, and execute workflows with auto-generated parameter editing, AI prompt assistant (Ollama), JSON syntax highlighting, Eagle integration, and multi-language support (EN/JA/ZH).\n- [**SOYLAB Comfy Router**](https://github.com/soylab-edu/ComfyUI-soylab-router) (⭐2) *pushed 19 hours ago*: Run Comfy Router image, video, and audio models from one ComfyUI node with provider selection and cost references.\n- [**VideoX-Fun**](https://github.com/aigc-apps/VideoX-Fun) (⭐2255) *pushed 20 hours ago*: VideoX-Fun is a video generation pipeline that can be used to generate AI images and videos, as well as to train baseline and Lora models for Diffusion Transformer. We support direct prediction from pre-trained baseline models to generate videos with different resolutions, durations, and FPS. Additionally, we also support users in training their own baseline and Lora models to perform specific style transformations.\n- [**Comfyui-DHan-NanoB-Gemini**](https://github.com/DHan315/Comfyui-DHan-NanoB-Gemini) (⭐0) *pushed 20 hours ago*: Gemini / Nano Banana image generation and editing nodes for ComfyUI, derived from ComfyUI-NanoB-Edit-Gemini.\n- [**SDVN_Comfy_node**](https://github.com/StableDiffusionVN/SDVN_Comfy_node) (⭐125) *pushed 20 hours ago*: Update support Qwen Image 2.1\n- [**JPEG is Fine**](https://github.com/a5ah1/jpeg-is-fine) (⭐0) *pushed 21 hours ago*: A focused JPEG-saving node for ComfyUI with 4:4:4 chroma subsampling and workflow preservation\n- [**ComfyUI Prompt Warehouse**](https://github.com/D33MO/ComfyUI-Prompt-Warehouse) (⭐0) *pushed 21 hours ago*: Prompt warehouse and workflow utility nodes for ComfyUI, including reusable prompts, multiline prompt editing, a persistent multi-LoRA loader, and deletable image output.\n- [**ComfyUI Mobile Frontend**](https://github.com/cosmicbuffalo/comfyui-mobile-frontend) (⭐86) *pushed 21 hours ago*: A mobile-friendly user interface for ComfyUI mounted in parallel with the main frontend at /mobile/.\n- [**Empty Latent Image Plus**](https://github.com/ukr8b3g-cmyk/Empty-Latent-Image-Plus) (⭐2) *pushed 21 hours ago*: A compact Empty Latent Image replacement that also outputs WIDTH and HEIGHT values for ComfyUI workflows.\n- [**Sonder Editor**](https://github.com/SonderSaid/ComfyUI-Sonder-Editor) (⭐5) *pushed 21 hours ago*: Timeline video editor for ComfyUI in a single node. Arrange video, images, and audio on tracks, set first and last frames, schedule prompts over time, transfer motion from a pose video, and regenerate any section in place. Work is organized into projects, and every result lands in a searchable asset gallery.\n- [**ComfyUI-LTX2.5-MSR**](https://github.com/liconstudio/ComfyUI-LTX2.5-MSR) (⭐35) *pushed 21 hours ago*: Multi-reference image conditioning nodes for LTX-2.5 in ComfyUI, using MSR slot embeddings and negative temporal offsets.\n- [**Kaski's Comfy Production Pack**](https://github.com/kaski23/Kaskis-Comfy-Production-Pack) (⭐0) *pushed 21 hours ago*: Production-focused ComfyUI nodes, API adaptions, runtime patches and workflow utilities.\n- [**ComfyUI-PixlStash**](https://github.com/Pikselkroken/ComfyUI-PixlStash) (⭐12) *pushed 21 hours ago*: Custom ComfyUI nodes for loading and saving images to a PixlStash vault.\n- [**ComfyUI_FunCode**](https://github.com/kaiery/ComfyUI_FunCode) (⭐0) *pushed 22 hours ago*: Custom ComfyUI node collection providing image tools (Load Image, Color Match, Canvas Editor) and LLM nodes for integration. (Description by CC)\n- [**M8 Nodes**](https://github.com/chenr5934-tech/ComfyUI-M8nodes) (⭐0) *pushed 22 hours ago*: M8 节点包：按货架分类的 ComfyUI 自定义节点 —— 大模型推理（远程 / 本地）、skill 装载、相机机位、多角色提示词，另带一个独立网页工作台\n- [**MOSS SoundEffect v2**](https://github.com/HuizhiXu/comfyui-moss-soundeffect-v2) (⭐0) *pushed 23 hours ago*: Text-to-sound-effect nodes for MOSS-SoundEffect v2. Picks a local model and runs inference in a compatible Python, creating one beside the node when needed.\n- [**Visual Suite (Studio Leiel)**](https://github.com/StudioLeiel/comfyui-visual-suite) (⭐2) *pushed 23 hours ago*: Seven visual nodes for ComfyUI: prompt composer with image reading, series lab, filename manager, save image with folder browsing, latent size picker, node bag and image crop.\n\n## Custom nodes created in 7 days\n\n- [**Kotodama Prompt Enhancer**](https://github.com/ericmey/comfyui-kotodama) (⭐0) *created 8 hours ago*: Text-to-image prompt enhancer for ComfyUI using an OpenAI-compatible chat endpoint\n- [**ComfyUI-BucketCrop**](https://github.com/malcolmamal/ComfyUI-BucketCrop) (⭐0) *created 8 hours ago*: Crop an image to the nearest training bucket ratio, centered on a detected region.\n- [**ComfyUI-MiniMaxH3RefLoRA**](https://github.com/malcolmamal/ComfyUI-MiniMaxH3RefLoRA) (⭐0) *created 8 hours ago*: One .safetensors holding a MiniMax H3 LoRA and its RefMod references.\n- [**ComfyUI-ASASR**](https://github.com/claussteinmassl/ComfyUI-ASASR) (⭐0) *created 12 hours ago*: ASASR 4x diffusion super-resolution (FLUX.1-dev dual-LoRA) for ComfyUI, with native fp8/GGUF support. Non-commercial (CC-BY-NC-4.0 weights).\n- [**Higgsfield API by Sherif Oneway**](https://github.com/w0ver/Higgsfield-api-comfyui-nodes) (⭐0) *created 12 hours ago*: Generate images and videos in ComfyUI with your own Higgsfield API credentials. Includes reference images, Seedance video generation, resumable requests, and local outputs. By Sherif Oneway.\n- [**ComfyUI LC Modelbuilder Nodes**](https://github.com/lonecatone23/ComfyUI_LC_ModelBuilder_nodes) (⭐0) *created 12 hours ago*: ComfyUI LC Modelbuilder Nodes by lonecatone23 — checkpoint/model merging tools. Starts with LC Krea2 Block Merge Advanced (per-block ratio curve + named-region sliders, reuses ComfyUI's own block-merge patching), checkpoint savers, and LC Face Variety Scorer (same-face test with InsightFace buffalo_l via onnxruntime). Companion to ComfyUI_LC123_nodes; separate Registry name.\n- [**Qwen Image 2.1 Fun ControlNet Union (T8)**](https://github.com/T8mars/Comfyui-Qwen-Image-2.1-Fun-Controlnet-Union-T8) (⭐1) *created 12 hours ago*: Native Qwen Image 2.1 Fun ControlNet Union loader and conditioning nodes for ComfyUI\n- [**ComfyUI-APIMaster**](https://github.com/apimaster-ai/ComfyUI-APIMaster) (⭐0) *created 16 hours ago*: ComfyUI nodes for image and video generation through APIMaster and other OpenAI-compatible gateways. No extra Python dependencies.\n- [**JPEG is Fine**](https://github.com/a5ah1/jpeg-is-fine) (⭐0) *created 21 hours ago*: A focused JPEG-saving node for ComfyUI with 4:4:4 chroma subsampling and workflow preservation\n- [**SOYLAB Comfy Router**](https://github.com/soylab-edu/ComfyUI-soylab-router) (⭐2) *created a day ago*: Run Comfy Router image, video, and audio models from one ComfyUI node with provider selection and cost references.\n- [**Ciru AMD Halo Qwen 2.1 Turbo**](https://github.com/ciru-ai/ComfyUI-CiruImageAccelerator) (⭐5) *created a day ago*: Qwen Image 2.1: Turbo Prediction and Strix Halo packed attention for text-to-image and image editing. Start edits with full evaluations; edit prediction is opt-in.\n- [**Zen Image Edit T8**](https://github.com/T8mars/comfyui-Zen-Image-Edit-T8) (⭐1) *created a day ago*: Native ComfyUI nodes for Zen Image Edit with a single-file Qwen-Image-2.1 checkpoint and student text encoder.\n- [**Wild H3C — MiniMax H3 for Apple Silicon**](https://github.com/skaiy/wild-h3c-comfyui) (⭐1) *created a day ago*: MiniMax H3 video generation on Apple Silicon, powered by the h3.c Metal engine.\n- [**Qwen-Image Photo Styles**](https://github.com/pottokao-dotcom/ComfyUI-QwenImage-PhotoStyles) (⭐11) *created a day ago*: A prompt-rewriter node for Qwen-Image-2.1: pick a photographic style (camera language + mood) and a PE-T2I rewriter turns a short prompt into a long English one, plus a negative prompt and aspect-ratio dimensions. Not a model loader.\n- [**Qwen Image 2.1 BlockCache T8**](https://github.com/T8mars/Comfyui-Qwen-Image-2.1-BlockCache-T8) (⭐8) *created a day ago*: Experimental native Qwen-Image-2.1 block cache, spectral forecasting, and attention adapters.\n- [**MOSS SoundEffect v2**](https://github.com/HuizhiXu/comfyui-moss-soundeffect-v2) (⭐0) *created a day ago*: Text-to-sound-effect nodes for MOSS-SoundEffect v2. Picks a local model and runs inference in a compatible Python, creating one beside the node when needed.\n- [**Bulent Gercek Nodes**](https://github.com/bulentgercek/bulentgercek-nodes) (⭐1) *created a day ago*: Prompt Builder, List Pick and String Line Count: text and list utility nodes for building and iterating prompts.\n- [**Qwen-Image 2.1 Prompt Enhancer (MTP)**](https://github.com/mozophe/ComfyUI-Qwen-Image-2.1-PromptEnhancer-MTP) (⭐1) *created 2 days ago*: ComfyUI nodes for Qwen-Image 2.1's official prompt enhancer, with MTP speculative decoding for faster generation.\n- [**M8 Nodes**](https://github.com/chenr5934-tech/ComfyUI-M8nodes) (⭐0) *created 2 days ago*: M8 节点包：按货架分类的 ComfyUI 自定义节点 —— 大模型推理（远程 / 本地）、skill 装载、相机机位、多角色提示词，另带一个独立网页工作台\n- [**ComfyUI-BCNodes**](https://github.com/0xBeycan/ComfyUI-BCNodes) (⭐0) *created 2 days ago*: Utility nodes for ComfyUI: logic, mask, image, PostFx film looks, dataset analysis (Caption Audit, Image Quality Gate), Social Media Export, SeedVR2 streaming, loaders and workflow helpers (AutoBypass, Anything Everywhere, comparers).\n- [**ComfyUI-VideoMaskEditor**](https://github.com/knoic/ComfyUI-VideoMaskEditor) (⭐0) *created 2 days ago*: Interactive video mask editor to fix mask flickering/missing frames from SAM/SAM3.1 before diffusion models or subject cropping.\n- [**ComfyUI-Kaola-Qwen-image2.1-prompt-rewrite**](https://github.com/kana112233/ComfyUI-kaola-qwen-image2.1-prompt-rewrite) (⭐2) *created 3 days ago*: A custom node for ComfyUI that integrates Qwen 2.1 prompt rewriting for t2i and image editing\n- [**Prompt \u0026 Dimensions from LLM**](https://github.com/BleynChannel/ComfyUI-QwenImage-PromptExtractor) (⭐2) *created 3 days ago*: ComfyUI custom node that resolves a Qwen Image 2.1 Prompt Enhancer JSON hint (rewritten prompt + aspect ratio/size) into a ready-to-use prompt and exact width/height.\n- [**ComfyUI-DiffHDR**](https://github.com/claussteinmassl/ComfyUI-DiffHDR) (⭐6) *created 3 days ago*: DiffHDR (LDR to HDR reconstruction for images, videos and HDRI panoramas) on ComfyUI's native Wan2.1-VACE.\n- [**Inferway H3**](https://github.com/inferway/comfyui-inferway) (⭐0) *created 3 days ago*: Inferway H3 video generation nodes for ComfyUI (inferway-comfy): text-to-video, first/last-frame video, reference-image video, task resume and remote cancel. Runs inferway/minimax-h3-768p through the Inferway API.\n- [**PRYX ComfyUI Higgsfield**](https://github.com/PRYX-STUDIO/pryx-comfyui-higgsfield) (⭐1) *created 3 days ago*: Generate and edit images and videos with Higgsfield from ComfyUI, using model-specific controls, connected media references, and estimate-first cost checks.\n- [**Lora Stack Pack**](https://github.com/makszlak/ComfyUI_lora_stack_pack) (⭐0) *created 3 days ago*: A custom node pack for multi-LoRA stacking and dynamic weight management\n- [**Qwen Image References Manager**](https://github.com/Hearmeman24/ComfyUI-QwenImageRefPack) (⭐0) *created 3 days ago*: Ten-image reference manager for Qwen Image.\n- [**ComfyUI Image Option Picker**](https://github.com/lalikamala/ComfyUI-ImageOptionPicker) (⭐0) *created 3 days ago*: A node to pause the workflow to select one of the three generated images for further processing.\n- [**Qwen Image 2.1 Prompt Rewrite T8**](https://github.com/T8mars/Comfyui-Qwen-Image-Prompt-Rewrite-T8) (⭐30) *created 3 days ago*: Local Qwen Image 2.1 prompt rewriting for text-to-image and 1-10 image editing in ComfyUI\n- [**ComfyUI-RH-Qwen-Image-2-1-diffusers**](https://github.com/RH-RunningHub/ComfyUI-RH-Qwen-Image-2-1-diffusers) (⭐0) *created 3 days ago*: Official diffusers Qwen-Image 2.1 pipeline as a ComfyUI node (unified text-to-image / image-conditioned generation) with ComfyUI DynamicVRAM streaming.\n- [**ComfyUI VideoMark（视频水印）**](https://github.com/kaerozhi/comfyui-videomark) (⭐2) *created 3 days ago*: Watermark nodes for video and image workflows: corner / center / floating / tiled placement, animated intro and outro copyright cards, text and PNG-logo overlays with adjustable outline and drop shadow, a visual panel for picking styles and uploading a logo, and English/Chinese UI. Works on any IMAGE batch, so it fits MiniMax H3 / Wan / LTX / Hunyuan / VHS / AnimateDiff frame pipelines. No extra dependencies beyond ComfyUI's bundled torch / numpy / Pillow.\n- [**ComfyUI-GZNodes**](https://github.com/shines77/ComfyUI-GZNodes) (⭐1) *created 4 days ago*: Various quality of life -nodes for ComfyUI, mostly just visual stuff to improve usability.\n- [**ComfyUI Model Hub**](https://github.com/licyk/comfyui-model-hub) (⭐1) *created 4 days ago*: Manage and download models with SD Model Hub inside ComfyUI.\n- [**Camera Path**](https://github.com/phazei/ComfyUI-Camera-Path) (⭐2) *created 4 days ago*: Reproject an image or clip through its MoGe geometry along a camera path authored in an interactive 3D editor.\n- [**From Mesh to Motion**](https://github.com/meryboth/from-mesh-to-motion) (⭐0) *created 4 days ago*: One rest-pose mesh to a registered keyframe sheet an auto-rigger can animate from.\n- [**From 3D to Campaign**](https://github.com/meryboth/from-3d-to-campaign) (⭐0) *created 4 days ago*: Turn a 3D model of a building into social-ready campaign assets: geometry-faithful renders, an automatic quality gate, validated copy and a laid-out post — all in one ComfyUI graph.\n- [**ComfyUI-SongLRC**](https://github.com/TheAwaken1/ComfyUI-SongLRC) (⭐4) *created 4 days ago*: Timed .lrc lyrics for generated songs, saved beside the audio, with a player that highlights each line as it is sung.\n- [**ComfyUI-SparkStudio**](https://github.com/TheAwaken1/ComfyUI-SparkStudio) (⭐0) *created 4 days ago*: Send a ComfyUI prompt to a DGX Spark or any OpenAI-compatible model server and get text back.\n- [**DeepSeek Prompt Chat**](https://github.com/lh658459/ComfyUI-DeepSeek-Prompt-Chat) (⭐0) *created 4 days ago*: Multi-session DeepSeek prompt chat for ComfyUI, with TXT knowledge retrieval, bilingual prompt tags, and confirmed English prompt output.\n- [**Richard's Video Kits**](https://github.com/Richard-Wang-fs/ComfyUI-RichardsVideoKits) (⭐0) *created 4 days ago*: ComfyUI video segment saving, Wan Animate 2 loops, and final assembly with source audio\n- [**ComfyUI Neo Sampler (Forge Neo)**](https://github.com/wangjue520/ComfyUI-Neo-Sampler) (⭐0) *created 4 days ago*: Replicates Forge Neo (neo branch) sampling, RNG and prompt encoding inside ComfyUI - same parameters, same results.\n- [**MLSuite**](https://github.com/marcolopezs/ComfyUI_MLSuite) (⭐0) *created 5 days ago*: MLSuite: a growing collection of ComfyUI nodes. Starts with Image Loader — bring any image into your workflow from an upload, a URL, a built-in gallery browser, or automatic folder rotation.\n- [**DashScope Image Generation**](https://github.com/GPleex/ComfyUI-DashscopeImage) (⭐0) *created 5 days ago*: ComfyUI custom node for image generation with Alibaba Cloud DashScope.\n- [**crypswolfy69 nodes**](https://github.com/babydjac/crypswolfy69-nodes) (⭐0) *created 5 days ago*: crypswolfy69 nodes — Alchemist (any-LLM prompts/captions), Prompt Rotate, and a Hugging Face model browser/downloader for ComfyUI.\n- [**ComfyUI-Hy-MT2**](https://github.com/1038lab/ComfyUI-Hy-MT2) (⭐0) *created 5 days ago*: Lightweight ComfyUI translation node for Tencent Hy-MT2 models powered by GGUF (llama.cpp). Fast, memory-efficient, and cleanly managed.\n- [**ComfyUI LC MaskMaker Nodes**](https://github.com/lonecatone23/ComfyUI_LC_MaskMaker_nodes) (⭐0) *created 5 days ago*: ComfyUI LC MaskMaker Nodes by lonecatone23: on-node Outpaint and Create Mask, background removal, Segment Anything, person masks, mask refine, image blend, auto adjust, depth and normal maps. Models load on demand and are labelled with their licenses. Companion to ComfyUI_LC123_nodes; separate Registry name.\n- [**ComfyUI-H3-upgrade-kit**](https://github.com/flywhale-666/ComfyUI-H3-upgrade-kit) (⭐3) *created 5 days ago*: MiniMax H3 semantic conditioning, audio frame-rate sync, latent upscaling, tiled sampling, batched VAE decoding, motion continuation and SelfLift sampling.\n- [**ComfyUI-Jev**](https://github.com/hndrr/ComfyUI-Jev) (⭐5) *created 5 days ago*: Jev text interpretation and judgments for ComfyUI: candidate selection, condition evaluation, scoring, number extraction, and local Skill selection. Includes OpenRouter text generation.\n- [**Universal Prompt Optimizer**](https://github.com/aihaipan/ComfyUI-Universal_Prompt_Optimizer) (⭐0) *created 5 days ago*: Universal prompt optimizer for any ComfyUI model, with R2V bridges for both MiniMax H3 Director and TimelineDirector.\n- [**ComfyUI-NodeSnapshots**](https://github.com/SparknightLLC/ComfyUI-NodeSnapshots) (⭐7) *created 6 days ago*: Individual node snapshots and bounded link caching for smoother ComfyUI workflow navigation.\n- [**ComfyUI-Bilingual-Prompt-Inspector**](https://github.com/mengshengzhijie/ComfyUI-Bilingual-Prompt-Inspector) (⭐1) *created 6 days ago*: Prompt translator and manager: bilingual Chinese-English tag view with drag-to-reorder and temporary hiding, upstream prompt interception, favorites, multiple translation services, and a sidebar dictionary manager.\n- [**Inkvec**](https://github.com/logolabs/inkvec-comfyui) (⭐0) *created 6 days ago*: ComfyUI nodes for Inkvec, the LogoLabs raster-to-SVG tracer: trace to SVG (with native transparency), save SVG, and JPEG/WebP denoise and x4 upscale for logos before tracing.\n- [**Continuity Metal**](https://github.com/audiohacking/ComfyUI-Continuity-Mac) (⭐4) *created 6 days ago*: Apple Silicon fork of Continuity: one node for MiniMax H3, LTX 2.5 and the still families on Metal / MPS\n- [**ComfyUI Input Thumbnails**](https://github.com/panjapongr/ComfyUI-InputThumbnails) (⭐0) *created 6 days ago*: A ComfyUI custom node that adds a fast, visual thumbnail gallery picker for browsing and selecting images from the input directory. Does not replace core Load Image.\n- [**MiniMax H3 Draft Continue**](https://github.com/ukr8b3g-cmyk/MiniMax-H3-T2VA-Draft-Continue) (⭐2) *created 6 days ago*: Review a predicted first frame, then continue the same MiniMax H3 sampling state with Preview/GO safety, Reference, structured BBOX, and Multi-Key support.\n\n## Custom nodes trending in 7 days\n\n- [**ComfyUI**](https://github.com/comfyanonymous/ComfyUI) (⭐134884 +1179) *pushed a minute ago*: A collection of nodes for powerful and more ordered prompting. This does not /help/ you prompt better, it just helps you organize your prompting spaghetti.\n- [**MiniMax H3 Director**](https://github.com/AIMixer/ComfyUI_MiniMaxH3_Director) (⭐1970 +183) *pushed a day ago*: Multi-segment MiniMax H3 Director — official MiniMaxH3ImageToVideo / ReferenceToVideo pipeline.\n- [**ComfyUI-Manager**](https://github.com/ltdrdata/ComfyUI-Manager) (⭐16256 +77) *pushed 19 hours ago*: ComfyUI-Manager itself is also a custom node.\n- [**ComfyUI-GGUF**](https://github.com/city96/ComfyUI-GGUF) (⭐4083 +71) *pushed 8 months ago*: GGUF Quantization support for native ComfyUI models\n- [**Photoshoot**](https://github.com/ralksta/ComfyUI-Photoshoot) (⭐140 +60) *pushed 3 days ago*: Build a person once, then shoot a whole series: framing, pose, placement, expression and aspect ratio vary while the person stays the same.\n- [**ComfyUI-DeGrid**](https://github.com/lunaaispace-eng/ComfyUI-DeGrid) (⭐63 +59) *pushed 4 days ago*: Removes the 2px pixel grid artifact from Qwen Image VAE decoded images with auto-calibration.\n- [**MiniMax H3 / Seedance / Music / YuE2 / Qwen Image Enhancer (T8)**](https://github.com/T8mars/comfyui-minimax-h3-prompt-enhancer-T8) (⭐316 +46) *pushed 2 days ago*: Enhance MiniMax H3 and Seedance 2.0 video prompts, Music 3 and YuE2 music text, and Qwen Image 2.1 image prompts with cloud or local GGUF LLM providers.\n- [**FastVideo**](https://github.com/hao-ai-lab/FastVideo) (⭐4501 +40) *pushed 2 hours ago*: A custom node suite for ComfyUI that provides accelerated multi-GPU video generation using [a/FastVideo](https://github.com/hao-ai-lab/FastVideo).\n- [**MiniMax H3 Activation Chunk - Star7**](https://github.com/star7code/minimax-h3-chunk-star7) (⭐58 +37) *pushed 3 days ago*: QKV/RoPE/MLP activation chunking for ComfyUI MiniMax H3 with selectable CK, SLA, Sol, and Hybrid attention paths.\n- [**MiniMax H3 Audio T8**](https://github.com/T8mars/comfyui-minimax-h3-audio-T8) (⭐1121 +37) *pushed 2 days ago*: MiniMax H3 joint AV, audio refine, long-video, reference control, motion analysis, temporal restoration, and acceleration nodes for ComfyUI\n- [**ComfyUI-FL-YuE2**](https://github.com/filliptm/ComfyUI-FL-YuE2) (⭐178 +36) *pushed a day ago*: YuE2 music generation, piano roll editing, and joint AR/NAR LoRA training for ComfyUI\n- [**VOSR 2.0**](https://github.com/ylchen333/ComfyUI-VOSR2) (⭐243 +36) *pushed 10 days ago*: ComfyUI node for VOSR 2.0 (one-step 1.4B) image super-resolution.\n- [**VNCCS - Collection of utility nodes**](https://github.com/AHEKOT/ComfyUI_VNCCS_Utils) (⭐1065 +36) *pushed 13 days ago*: VNCCS utility nodes: Pose Studio, UniCanvas, and 3D Factory.\n- [**H3 Motion Context**](https://github.com/NikoDemon80/ComfyUI-H3-Motion-Context) (⭐1011 +35) *pushed 18 days ago*: Clip chaining for MiniMax H3 in ComfyUI: pin the tail of the previous clip, picture and sound, so the next clip genuinely continues it. The picture is sliced out of the previous latent with no VAE round trip, and the pinned audio window ends at the join and reaches backwards, so the soundtrack continues rather than restarts. ComfyUI is not modified. Node ids MiniMaxH3MotionContext, MiniMaxH3MotionContextTrim, MiniMaxH3MotionContextSaveLatent, MiniMaxH3MotionContextLoadLatent, MiniMaxH3MotionContextChain, MiniMaxH3MotionContextSeamProbe.\n- [**Krea 2 Identity Edit**](https://github.com/lbouaraba/comfyui-krea2edit) (⭐659 +33) *pushed a month ago*: Krea 2 Identity Edit — in-context instruction-edit nodes for the Krea 2 model: source-image appearance preservation (VAE reference tokens + 3D-RoPE), image-grounded instruction encoding, a reference-fidelity dial (ref_boost), and the training-matched FIT reference geometry.\n- [**Prompt Assistant**](https://github.com/yawiii/ComfyUI-Prompt-Assistant) (⭐2372 +32) *pushed 5 months ago*: A versatile prompt utility featuring translation, refinement, expansion, and image/video-to-prompt reverse engineering with one-click access to any online or local LLM.\n- [**ComfyUI MiniMax H3 Extender**](https://github.com/tritant/ComfyUI_MiniMax_H3_Extender) (⭐258 +32) *pushed 2 days ago*: ComfyUI node for MiniMax H3 that chains multiple video clips with motion context, disk caching, dynamic image references, audio reference support, and seamless final video/audio decoding.\n- [**ComfyUI-MiniMaxH3-Easy**](https://github.com/nkxx188/ComfyUI-MiniMaxH3-Easy) (⭐776 +31) *pushed 6 days ago*: A streamlined MiniMax H3 workflow for text-to-video, image-to-video, and reference-to-video generation in ComfyUI.\n- [**ComfyUI-H3-FaceRefine**](https://github.com/Carasibana/ComfyUI-H3-FaceRefine) (⭐435 +29) *pushed 12 days ago*: Refine and improve the quality of small faces in MiniMax H3 video: per-frame face tracking, normalised crops, AV-latent injection and feathered stitch-back.\n- [**MiniMax H3 Image Studio**](https://github.com/astropuzzo/ComfyUI-MiniMax-H3-Image-Studio) (⭐186 +27) *pushed 12 days ago*: ComfyUI nodes and workflows for MiniMax H3 image generation and editing.\n- [**ComfyUI-MAINodes**](https://github.com/matlowai/ComfyUI-MAINodes) (⭐203 +26) *pushed 4 days ago*: MatlowAI's MiniMax-H3 nodes: Contact-Sheet diffusion + Motion Lab (test-time de-roping of fast motion via oracle-guided v2v time-smear)\n- [**KJNodes for ComfyUI**](https://github.com/kijai/ComfyUI-KJNodes) (⭐3317 +24) *pushed 11 days ago*: Various quality of life -nodes for ComfyUI, mostly just visual stuff to improve usability.\n- [**VNCCS - Visual Novel Character Creation Suite**](https://github.com/AHEKOT/ComfyUI_VNCCS) (⭐1608 +23) *pushed 12 days ago*: VNCCS is a comprehensive tool for creating character sprites for visual novels.\n- [**ComfyTV**](https://github.com/jtydhr88/ComfyTV) (⭐1037 +22) *pushed a day ago*: LibTV-style Canvas pipeline for ComfyUI\n- [**H3 Prompt Writer**](https://github.com/duckyshell/ComfyUI-MiniMaxH3-Prompt-Writer) (⭐226 +21) *pushed a day ago*: A multimodal MiniMax H3 prompt-writing extension for ComfyUI with local and API providers.\n- [**MiniMax H3 RefMod**](https://github.com/Luisacaotica/ComfyUI-MiniMaxH3Mod) (⭐226 +21) *pushed 8 days ago*: Extract, save and combine reusable MiniMax H3 image, video and audio references as RefMod safetensors, with a unified Master extractor, library, inspector and strength curves.\n- [**YuE2 Music**](https://github.com/pytraveler/YuE2-ComfyUI) (⭐52 +20) *pushed 8 hours ago*: ComfyUI nodes for YuE2-3B: a style description and lyrics become a readable score and then a complete 48 kHz stereo song, generated locally.\n- [**ComfyUI-Easy-Media**](https://github.com/yolain/ComfyUI-Easy-Media) (⭐207 +20) *pushed a day ago*: A ComfyUI custom node package for streamlined media loading and video pipeline assembly. Provides intuitive nodes that simplify media resource loading with user-friendly parameters, making it easier to build and configure video processing workflows.\n- [**rgthree's ComfyUI Nodes**](https://github.com/rgthree/rgthree-comfy) (⭐3496 +19) *pushed an hour ago*: Nodes: Seed, Reroute, Context, Lora Loader Stack, Context Switch, Fast Muter. These custom nodes helps organize the building of complex workflows.\n- [**ComfyUI-See-through**](https://github.com/jtydhr88/ComfyUI-See-through) (⭐807 +19) *pushed a month ago*: ComfyUI nodes for See-through: Anime Layer Decomposition from a Single Image\n- [**MiniMax H3 Contex Loop**](https://github.com/ethanfel/ComfyUI-MiniMaxH3-Contex-Loop) (⭐463 +17) *pushed 14 hours ago*: Recursive MiniMax H3 scene loops with motion and audio continuity, visual planning, review gates, atomic checkpoints, resume, and final video assembly.\n- [**ComfyUI-Lora-Manager**](https://github.com/willmiao/ComfyUI-Lora-Manager) (⭐1484 +16) *pushed a day ago*: Revolutionize your workflow with the ultimate LoRA companion for ComfyUI!\n- [**XB_ToolBox**](https://github.com/WJLUOXIAO/XB_ToolBox) (⭐330 +16) *pushed a day ago*: A comprehensive ComfyUI extension suite encompassing both front-end interaction and low-level memory scheduling, designed to help beginners master workflows and simplify local deployment.\n- [**Qwen H3 Prompt**](https://github.com/chflame163/ComfyUI_Qwen_H3_Prompt) (⭐113 +16) *pushed 2 days ago*: Generate MiniMax H3 prompts locally with Qwen models in ComfyUI.\n- [**ComfyUI-EditUtils**](https://github.com/lrzjason/ComfyUI-EditUtils) (⭐235 +16) *pushed 4 days ago*: A collection of utility nodes for advanced image editing in ComfyUI, supporting multiple AI models including Qwen and Flux2Klein.\n- [**YuE2 Music T8**](https://github.com/T8mars/Comfyui-YuE2-T8) (⭐73 +16) *pushed 4 days ago*: Local YuE2 generation, MuLaCover rearrangement, notation, transcription, training, and voice workflows for ComfyUI\n- [**NKD Basic Tools**](https://github.com/Nekodificador/ComfyUI-NKD-Basic-Tools) (⭐145 +16) *pushed 7 days ago*: Everyday utility nodes for ComfyUI: inpaint crop \u0026 stitch, upright face crop \u0026 stitch with automatic masks, a live face rig for portrait expressions, hand-drawn vector masks, a paint canvas for scribbles and ControlNet guides, path and field blur, mask painting and cleanup, colour grading, gradients, noise and grain — each with a live preview in the node.\n- [**MiniMax H3 LongMedia**](https://github.com/vizart-vj/ComfyUI-MiniMax-H3-LongMedia) (⭐260 +14) *pushed 2 days ago*: Long-form MiniMax H3 video/audio generation for ComfyUI with unified clip planning, continuity, lip-sync, and adaptive low-VRAM execution.\n- [**MiniMax H3 Guide**](https://github.com/ethanfel/ComfyUI-MiniMax-H3-Guide) (⭐284 +14) *pushed a month ago*: A guided MiniMax H3 prompt preparation node for ComfyUI\n- [**Fantastic H3 Prompt Builder**](https://github.com/Adudeguyman/ComfyUI-Fantastic-MiniMaxH3-PromptBuilder) (⭐215 +14) *pushed 7 days ago*: Guided prompt writing and reference media handling for the MiniMax H3 video model: fillable templates for every mode, live checking against MiniMax's prompt guide, and a drag-and-drop media loader that keeps reference tags straight.\n- [**ComfyUI-RMBG**](https://github.com/1038lab/ComfyUI-RMBG) (⭐2125 +13) *pushed a month ago*: A sophisticated ComfyUI custom node engineered for advanced image background removal and precise segmentation of objects, faces, clothing, and fashion elements. This tool leverages a diverse array of models, including RMBG-2.0, INSPYRENET, BEN, BEN2, BiRefNet models, SAM, and GroundingDINO, while also incorporating a new feature for real-time background replacement and enhanced edge detection for improved accuracy.\n- [**ComfyUI-SeedVR2_VideoUpscaler**](https://github.com/numz/ComfyUI-SeedVR2_VideoUpscaler) (⭐2869 +13) *pushed 8 months ago*: Welcome to the ComfyUI-SeedVR2 Video Upscaler repository! This project offers a non-official video upscaling tool designed specifically for ComfyUI. With this tool, you can enhance your video quality, making your visual content more engaging and clearer.\n- [**Music Production Toolkit**](https://github.com/jplenio/ComfyUI-MiniMax-Music-Production-Toolkit) (⭐64 +13) *pushed 4 days ago*: ComfyUI music production with YuE2 audio cover versions, SheetSage2 score-aware prompts, YuE2 and MiniMax Music 3 song generation, restoration, mastering, artwork and release metadata.\n- [**BUNNY_H3_Conditioning_Bridge**](https://github.com/aa335615543-ux/BUNNY_H3_Conditioning_Bridge) (⭐26 +13) *pushed 11 days ago*: Semantic conditioning bridge for MiniMax H3.\n- [**Anima-Tools**](https://github.com/nregret/Comfyui-Anima-Tools) (⭐333 +12) *pushed 9 days ago*: ComfyUI nodes for anime prompt selection, random prompt generation, background and character tag composition, and Anima LoRA search, download, and loading.\n- [**Comfyui-MMH3-UltimateUpscale**](https://github.com/bbaudio-2025/Comfyui-MMH3-UltimateUpscale) (⭐210 +12) *pushed a day ago*: Upscale long, high-resolution MiniMax H3 video on a VRAM-limited GPU in a single node.\n- [**MiniMax H3 Semantic Bridge**](https://github.com/Speach1sdef178/MiniMax-H3-Semantic-Bridge) (⭐17 +12) *pushed 15 days ago*: A compact conditioning-space semantic bridge for MiniMax H3 FL2VA in ComfyUI.\n- [**ComfyUI's ControlNet Auxiliary Preprocessors**](https://github.com/Fannovel16/comfyui_controlnet_aux) (⭐4198 +11) *pushed 28 days ago*: Plug-and-play ComfyUI node sets for making ControlNet hint images.\n- [**ComfyUI Easy Use**](https://github.com/yolain/ComfyUI-Easy-Use) (⭐2762 +11) *pushed 3 days ago*: To enhance the usability of ComfyUI, optimizations and integrations have been implemented for several commonly used nodes.\n- [**ComfyUI-qwenmultiangle**](https://github.com/jtydhr88/ComfyUI-qwenmultiangle) (⭐1377 +11) *pushed 12 days ago*: A ComfyUI node for 3D camera angle control, outputs angle prompts for multi-angle image generation\n- [**ComfyUI GGUF (molbal's fork)**](https://github.com/molbal/ComfyUI-GGUF) (⭐76 +11) *pushed 4 days ago*: Actively maintained fork of ComfyUI-GGUF node pack with support for new models, INT8/INT4 GGUFs and optionally ComfyUI Dynamic VRAM\n- [**WhatDreamsCost-ComfyUI**](https://github.com/WhatDreamsCost/WhatDreamsCost-ComfyUI) (⭐2056 +11) *pushed a month ago*: LTX Director and a variety of other custom ComfyUI nodes and workflows\n- [**VRGameDevGirl Video Enhancement Nodes**](https://github.com/vrgamegirl19/comfyui-vrgamedevgirl) (⭐733 +10) *pushed an hour ago*: Film grain and color match nodes designed for high-quality frame-by-frame video enhancement in ComfyUI.\n- [**H3 Continuum**](https://github.com/ukr8b3g-cmyk/ComfyUI-H3-Continuum) (⭐109 +10) *pushed 2 days ago*: Long-form MiniMax H3 video generation for ComfyUI with AV latent continuation, reference conditioning, chunked sampling, and resume support.\n- [**ComfyUI-Pixaroma**](https://github.com/pixaroma/ComfyUI-Pixaroma) (⭐403 +10) *pushed 10 hours ago*: Creative suite for ComfyUI: fullscreen Image Composer, Paint, 3D Builder, Image Crop and AudioReact editors, plus Load/Save Image, Save Mp4, Load Video, Inpaint Crop and Stitch, Outpaint, XY Plot, Prompt library, LoRA Loader, Control Panel, Notes, Labels, and canvas tools for aligning and grouping nodes.\n- [**ComfyUI-ClipProj**](https://github.com/nicolab28/ComfyUI-ClipProj) (⭐162 +10) *pushed a month ago*: Swap a large text encoder for a small one with a learned linear projection. Cuts MiniMax H3 conditioning from 15.7 GB to 5.2 GB.\n- [**MiniMax-H3 Prompt Rewriter**](https://github.com/pytraveler/MiniMax-H3-Prompt-Rewriter-ComfyUI) (⭐195 +10) *pushed 10 days ago*: ComfyUI nodes that rewrite a short prompt into a structured MiniMax-H3 audio-video description, fully local: the LightX2V Prompt Rewriter LoRAs on Qwen3.6-27B or on multimodal Qwen3-VL-8B, which reads the reference frames itself, or MiniMax's own writing guide on any small GGUF for T2VA, I2VA, FL2VA, L2VA and Ref2VA, with a multimodal captioner for the reference assets - or one universal node that describes the references and writes the prompt together, with their order a widget.\n- [**ComfyUI-VideoHelperSuite**](https://github.com/Kosinkadink/ComfyUI-VideoHelperSuite) (⭐1854 +9) *pushed 22 days ago*: Nodes related to video workflows\n- [**ComfyUI-LTXVideo**](https://github.com/Lightricks/ComfyUI-LTXVideo) (⭐4142 +9) *pushed 9 hours ago*: Custom nodes for LTX-Video support in ComfyUI\n- [**comfyui-krea2-controlnet**](https://github.com/facok/comfyui-krea2-controlnet) (⭐232 +9) *pushed 2 months ago*: Native-style ComfyUI nodes for Krea2 Control LoRA inference. The plugin keeps ComfyUI's built-in Krea2 inference path intact, uses the expanded input projection from the LoRA checkpoint during sampling, and injects a VAE-encoded control latent.\n- [**ComfyUI-Copilot**](https://github.com/AIDC-AI/ComfyUI-Copilot) (⭐5528 +9) *pushed 14 days ago*: Your Intelligent Assistant for Comfy-UI.\n- [**comfyui-klein-edit-composite**](https://github.com/supermansundies/comfyui-klein-edit-composite) (⭐116 +9) *pushed 6 months ago*: A ComfyUI node that intelligently composites a generated (AI-edited) image back onto an original image by detecting only what actually changed between the two images and blending the generated content in cleanly.\n- [**ComfyUI-Spectrum-MiniMax-H3**](https://github.com/xmarre/ComfyUI-Spectrum-MiniMax-H3) (⭐668 +9) *pushed 5 days ago*: A ComfyUI custom node implementing Spectrum spectral feature forecasting for native MiniMax H3 audio-video generation.\n- [**MaskVidExperiments**](https://github.com/drozbay/MaskVidExperiments) (⭐206 +9) *pushed 13 days ago*: Video masking tools for ComfyUI: jitter-free subject-tracked crop and uncrop with feathered mask-confined pasting, video mask cleanup, and pixel-to-latent mask reduction aligned to causal video VAE frame grouping.\n- [**comfyui-reactor-node**](https://github.com/Gourieff/ComfyUI-ReActor) (⭐1366 +8) *pushed 3 days ago*: The Fast and Simple Face Swap Extension Node for ComfyUI, based on ReActor SD-WebUI Face Swap Extension\n- [**Use Everywhere (UE Nodes)**](https://github.com/chrisgoringe/cg-use-everywhere) (⭐1037 +8) *pushed 2 months ago*: A set of nodes that allow data to be 'broadcast' to some or all unconnected inputs. Greatly reduces link spaghetti.\n- [**RES4LYF**](https://github.com/ClownsharkBatwing/RES4LYF) (⭐1331 +8) *pushed a day ago*: Advanced samplers with new noise scaling math to enable SDE sampling with all publicly available native models; new unsampling/noise inversion methods and other advanced img2img techniques for inpainting and/or guiding the sampling process with guide images, with results superior to FlowEdit, RF Inversion, and other SOTA implementations. Also new style transfer methods unique to this node pack; regional conditioning for HiDream, Flux, AuraFlow, and WAN; methods for eliminating Flux blur; and temporal conditioning (shift gradually from one prompt to the next with video). 115 sampler types, 24 noise types, 11 noise scaling modes, in a single node. Also includes a wide variety of QoF and other utility nodes for boosting detail, manipulating sigmas, latents, images, and more.\n- [**TTS Audio Suite**](https://github.com/diodiogod/TTS-Audio-Suite) (⭐1213 +8) *pushed 5 days ago*: TTS Audio Suite - Universal multi-engine TTS extension for ComfyUI with unified architecture supporting ChatterBox, F5-TTS, and future engines like RVC. Features modular engine adapters, character voice management, comprehensive SRT subtitle support, and advanced audio processing capabilities.\n- [**ComfyUI-PixelDriftFix**](https://github.com/Mozer/ComfyUI-PixelDriftFix) (⭐38 +8) *pushed 3 months ago*: A ComfyUI custom node designed to eliminate pixel drifting, stretching, and minor cropping inconsistencies between a source image and an edited/upscaled version.\n- [**comfyui-obvpm**](https://github.com/chanon/comfyui-obvpm) (⭐54 +8) *pushed 10 hours ago*: Bundle multiple wires into one wire. Create customizable Presets nodes. Compose ref images in one node. ComfyUI nodes to save time and keep your workflows tidy.\n- [**MiniMax H3 Studio**](https://github.com/thaakeno/ComfyUI-MiniMax-H3-Studio) (⭐115 +8) *pushed 3 days ago*: A reference-aware MiniMax H3 still-image studio for ComfyUI\n- [**ComfyUI-YuE2-Trainer**](https://github.com/Starnodes2024/ComfyUI-YuE2-Trainer) (⭐61 +8) *pushed 10 days ago*: NODES: ComfyUI-YuE2-Trainer - Experimental trainer nodes for YuE2\n- [**WAS Node Suite v3**](https://github.com/WASasquatch/was-node-suite-comfyui) (⭐1852 +8) *pushed a day ago*: WAS-NS reborn; Tools for image processing, filters, masking, text, logic, numbers, latents, files, 3D scenes, and animation.\n- [**PixelOE**](https://github.com/KohakuBlueleaf/PixelOE) (⭐506 +8) *pushed 5 hours ago*: Detail-Oriented Pixelization based on Contrast-Aware Outline Expansion.\n- [**ComfyUI-Custom-Scripts**](https://github.com/pythongosssss/ComfyUI-Custom-Scripts) (⭐3198 +7) *pushed 7 months ago*: Enhancements \u0026 experiments for ComfyUI, mostly focusing on UI features\n- [**ComfyUI-WanVideoWrapper**](https://github.com/kijai/ComfyUI-WanVideoWrapper) (⭐6711 +7) *pushed 4 months ago*: ComfyUI wrapper nodes for [a/WanVideo](https://github.com/Wan-Video/Wan2.1) and related models.\n- [**ComfyUI Layer Style**](https://github.com/chflame163/ComfyUI_LayerStyle) (⭐3168 +7) *pushed 9 days ago*: A set of nodes for ComfyUI it generate image like Adobe Photoshop's Layer Style. the Drop Shadow is first completed node, and follow-up work is in progress.\n- [**comfyui-photoshop**](https://github.com/NimaNzrii/comfyui-photoshop) (⭐1755 +7) *pushed a month ago*: Powerfull bridge to Photoshop by NimaNzrii\n- [**TIPO-extension**](https://github.com/KohakuBlueleaf/z-tipo-extension) (⭐634 +7) *pushed a month ago*: A general extension to utilize TIPO or DanTagGen to do 'text-presampling' based on KGen library: [a/https://github.com/KohakuBlueleaf/KGen](https://github.com/KohakuBlueleaf/KGen)\n- [**ComfyUI-MultiGPU**](https://github.com/pollockjj/ComfyUI-MultiGPU) (⭐990 +7) *pushed 4 days ago*: This extension adds CUDA device selection to supported loader nodes in ComfyUI. By monkey-patching ComfyUI’s memory management, each model component (like UNet, Clip, or VAE) can be loaded on a specific GPU. Examples included are multi-GPU workflows for SDXL, FLUX, LTXVideo, and Hunyuan Video for both standard and GGUF loader nodes.\n- [**ComfyUI-Trellis2**](https://github.com/visualbruno/ComfyUI-Trellis2) (⭐840 +7) *pushed 16 days ago*: ComfyUI Wrapper for TRELLIS.2 - Microsoft's image-to-3D generation model. (Description by CC)\n- [**CGlide**](https://github.com/CGlide/ComfyUI-CGlide) (⭐77 +7) *pushed 7 days ago*: H3 Studio and friends — MiniMax H3 prompt building, animated sampling preview, video encoding and clip joining\n- [**Krea 2 and MiniMax H3 Pixel Art Refiners**](https://github.com/envy-ai/ComfyUI-Krea2-Pixel-Art-Refiner) (⭐13 +7) *pushed 2 days ago*: Refine Krea 2 and MiniMax H3 output with automatic or controlled pixel-grid collapse and perceptual palette reduction.\n- [**ComfyUI-MiniMax-H3-Promptor**](https://github.com/1038lab/ComfyUI-MiniMax-H3-Promptor) (⭐235 +7) *pushed 12 days ago*: ComfyUI-Minimax-H3-Promptor custom node for ComfyUI provides automation suite for generating MiniMax H3 prompts.\n\n## Custom nodes pushed in 7 days\n\n- [**ComfyUI**](https://github.com/comfyanonymous/ComfyUI) (⭐134884) *pushed a minute ago*: A collection of nodes for powerful and more ordered prompting. This does not /help/ you prompt better, it just helps you organize your prompting spaghetti.\n- [**ComfyUI-TagForge**](https://github.com/huchukato/ComfyUI-TagForge) (⭐11) *pushed 6 minutes ago*: Tag completion with a1111-style wildcard sub-selection, CSV database support (Danbooru, e621), multiple wildcard sources, and smart parsing for professional prompt engineering in ComfyUI.\n- [**ComfyUI-OldTimeRadio**](https://github.com/jbrick2070/ComfyUI-OldTimeRadio) (⭐11) *pushed 7 minutes ago*: Press Queue once: ComfyUI writes or adapts a radio play, casts and performs it with neural voices, composes the score, and cuts a finished episode video -- all locally. No account, no API key, nothing paid. Needs an NVIDIA card with 8 GB or more, a 16 GB Apple Silicon Mac, or a CPU (start ComfyUI with --cpu), plus about 25 GB of free disk; the first run fetches roughly 12 GB of models.\n- [**TEX Wrangle**](https://github.com/xavinitram/TEX) (⭐4) *pushed 13 minutes ago*: TEX (Tensor Expression Language). Per-pixel DSL for ComfyUI\n- [**SimpleSyrup**](https://github.com/Artificial-Sweetener/SimpleSyrup) (⭐2) *pushed 24 minutes ago*: Workflow-focused ComfyUI extensions for image generation.\n- [**ComfyUI-Model-Manager-Neo**](https://github.com/rikunarita/ComfyUI-Model-Manager-Neo) (⭐1) *pushed 32 minutes ago*: Manage models: browsing, download and delete. Fork of ComfyUI-Model-Manager with improved HF/Civitai auth, huggingface_hub integration, and bug fixes.\n- [**QwenVL-Mod: Enhanced Vision-Language**](https://github.com/huchukato/ComfyUI-QwenVL-Mod) (⭐110) *pushed 33 minutes ago*: Enhanced QwenVL node with MiniMax H3 loop mode and presets, multilingual prompt generation, camera \u0026 style tag dropdowns, Pony prompt converters, Qwen 3.8 uncensored models, GGUF backend, LTX 2.3 FL2VA presets, and local model discovery for professional multimodal video workflows.\n- [**Neo Nodes**](https://github.com/neoneo-ai/ComfyUI-Neo-Nodes) (⭐1) *pushed 37 minutes ago*: ComfyUI 的 AI 提示词工作台 + Krea2 生图套件——用在线/本地大模型（支持推理/thinking 模型）一键增强、生成与反推提示词，并内置 Krea2 文生图/参考图四视图、媒体素材库与配方库，一键修复路径等便捷功能\n- [**Mochorong Nodes**](https://github.com/mochorongo/Mochorong) (⭐0) *pushed an hour ago*: Utility nodes for ComfyUI — audio gates, selectors, conditional routing, and type conversion.\n- [**ComfyUI LC123 Nodes**](https://github.com/lonecatone23/ComfyUI_LC123_nodes) (⭐22) *pushed an hour ago*: ComfyUI LC123 Nodes by lonecatone23 — Image Label, Skin Upscale, Bypass Relay, Image/Mask Pass, Widget To String, Save Image + Metadata, Any Empty Bool/Int/Float, Int Split, LC Batch Image, Tone Match, Color Match mask, MiniMax H3 pipe, Image-Mask Resize, LC Lighting Control, Photo Style, Skin Beauty, Sharpen Pro, prompt builder, sampler configure, Sigma Curve, Sigma Resample, image FX, pipes, notify.\n- [**Camera Path**](https://github.com/phazei/ComfyUI-Camera-Path) (⭐2) *pushed an hour ago*: Reproject an image or clip through its MoGe geometry along a camera path authored in an interactive 3D editor.\n- [**WextraUI**](https://github.com/sickbraintwo/WextraUI) (⭐0) *pushed an hour ago*: Extra nodes for ComfyUI, from the Winteraction workbench. Time works for you: WextraUI nodes have a control after generate and the carry that links them, so a queue of runs changes checkpoint, LoRA, sampler, scheduler, seed, frame and prompt on its own, and WSave Image puts every image in the right place with a file name built from parts. One press of Run and the machine never stops. Twenty nodes: WCheckpoint, WLoRA, WSampler, WScheduler, WInt, WFloat, WSwitch, WRoute, WDifference, WFrame, WPrompt Rows and the WScene / WLoop family for MiniMax H3.\n- [**ComfyUI-Prompt-Manager**](https://github.com/FranckyB/ComfyUI-Prompt-Manager) (⭐157) *pushed an hour ago*: A simple custom node for ComfyUI that allows you to save and reuse prompts, organized into different categories\n- [**CometAPI**](https://github.com/jieg9341-lab/ComfyUI-CometAPI) (⭐17) *pushed an hour ago*: A multimodal API workflow toolkit for ComfyUI with image, video, audio, text, batch generation, asset cards, and an integrated chat assistant.\n- [**rgthree's ComfyUI Nodes**](https://github.com/rgthree/rgthree-comfy) (⭐3496) *pushed an hour ago*: Nodes: Seed, Reroute, Context, Lora Loader Stack, Context Switch, Fast Muter. These custom nodes helps organize the building of complex workflows.\n- [**Pruna nodes for ComfyUI**](https://github.com/PrunaAI/ComfyUI_pruna) (⭐66) *pushed an hour ago*: This repository explains how to accelerate image generation in ComfyUI using Pruna, an inference optimization engine that makes AI models faster, smaller, cheaper, and greener. ComfyUI is a popular node-based GUI for image generation models, for which we provide a custom compilation node that accelerates Stable Diffusion (SD) and Flux inference, while preserving output quality.\n- [**WeiLin-Comfyui-Tools**](https://github.com/weilin9999/WeiLin-Comfyui-Tools) (⭐536) *pushed an hour ago*: quickly use the prompt word tool in ComfyUI\n- [**VRGameDevGirl Video Enhancement Nodes**](https://github.com/vrgamegirl19/comfyui-vrgamedevgirl) (⭐733) *pushed an hour ago*: Film grain and color match nodes designed for high-quality frame-by-frame video enhancement in ComfyUI.\n- [**ComfyUI-RIFE-TensorRT-Auto**](https://github.com/huchukato/ComfyUI-RIFE-TensorRT-Auto) (⭐6) *pushed an hour ago*: Ultra fast video frame interpolation for ComfyUI using RIFE with TensorRT acceleration. Auto-detects CUDA version, installs matching TensorRT wheels, and downloads RIFE models automatically.\n- [**ComfyUI-Upscaler-TensorRT-Auto**](https://github.com/huchukato/ComfyUI-Upscaler-TensorRT-Auto) (⭐2) *pushed an hour ago*: Fast image upscaling for ComfyUI using TensorRT acceleration (2-4x faster than standard methods). Auto-detects CUDA version and installs matching TensorRT wheels. Supports multiple upscaling models with automatic engine building and optimized inference for NVIDIA GPUs.\n- [**ComfyUI-HuggingFace**](https://github.com/huchukato/ComfyUI-HuggingFace) (⭐8) *pushed an hour ago*: HuggingFace model downloader for ComfyUI — search, download, and organize AI models directly within your workflow with integrated Civitai repository access and batch download support.\n- [**Perfect Video Resolution**](https://github.com/huchukato/ComfyUI-PerfectVideoResolution) (⭐5) *pushed an hour ago*: Automatically calculates and applies the optimal resolution for Wan 2.2, MiniMax H3, and LTX video generation models based on aspect ratio and model requirements.\n- [**ComfyUI-Xz3r0-Nodes**](https://github.com/Xz3r0-M/ComfyUI-Xz3r0-Nodes) (⭐14) *pushed 2 hours ago*: Custom ComfyUI nodes: XMath, XResolution, XImageSave, XLatentLoad, XLatentSave, XVideoSave, XAudioSave, XStringGroup, XWorkflowSave, XMetadataWorkflow(Extension), XDateTimeString, XFitView(Extension) ...and more\n- [**H3 Project Suite**](https://github.com/Adudeguyman/ComfyUI-H3-Project-Suite) (⭐38) *pushed 2 hours ago*: Long-form video with MiniMax H3. Chain clips that genuinely continue each other in picture and sound, managed as a project with review, takes, branching and one-click export. Each clip is handed to the next in latent space, so no decode and re-encode round trip sits between them.\n- [**LanPaint**](https://github.com/scraed/LanPaint) (⭐1404) *pushed 2 hours ago*: Achieve seamless inpainting results without needing a specialized inpainting model.\n- [**ComfyUI-RPG-Characters**](https://github.com/lord-lethris/ComfyUI-RPG-Characters) (⭐7) *pushed 2 hours ago*: Stylized RPG character prompt generator for ComfyUI. Supports standard and Ollama-based prompts, works with SD, SDXL, Flux, and more.\n- [**FastVideo**](https://github.com/hao-ai-lab/FastVideo) (⭐4501) *pushed 2 hours ago*: A custom node suite for ComfyUI that provides accelerated multi-GPU video generation using [a/FastVideo](https://github.com/hao-ai-lab/FastVideo).\n- [**MiniMax H3 Flow-Aligned Regenerate**](https://github.com/xmarre/MiniMax-H3-Flow-Aligned-Regenerate) (⭐16) *pushed 3 hours ago*: H3-native flow-aligned and progressive-resolution regeneration for ComfyUI\n- [**ComfyUI-mnemic-nodes**](https://github.com/MNeMoNiCuZ/ComfyUI-mnemic-nodes) (⭐105) *pushed 3 hours ago*: Added Lora Loader - Tag node, originally by badjeff\n- [**ComfyUI Eclipse**](https://github.com/r-vage/ComfyUI_Eclipse) (⭐36) *pushed 3 hours ago*: Comprehensive ComfyUI custom node suite featuring Smart Prompt with wildcards, a pipe ecosystem, universal type converters, image/video utilities, and workflow helpers. V3 API, Nodes 2.0 compatible.\n- [**ComfyUI LC MaskMaker Nodes**](https://github.com/lonecatone23/ComfyUI_LC_MaskMaker_nodes) (⭐0) *pushed 4 hours ago*: ComfyUI LC MaskMaker Nodes by lonecatone23: on-node Outpaint and Create Mask, background removal, Segment Anything, person masks, mask refine, image blend, auto adjust, depth and normal maps. Models load on demand and are labelled with their licenses. Companion to ComfyUI_LC123_nodes; separate Registry name.\n- [**comfyui_AcademiaSD**](https://github.com/AcademiaSD/comfyui_AcademiaSD) (⭐80) *pushed 4 hours ago*: Official set of custom nodes of AcademiaSD.\n- [**PixelOE**](https://github.com/KohakuBlueleaf/PixelOE) (⭐506) *pushed 5 hours ago*: Detail-Oriented Pixelization based on Contrast-Aware Outline Expansion.\n- [**Comfyui-DHan-Stasis**](https://github.com/DHan315/Comfyui-DHan-Stasis) (⭐0) *pushed 5 hours ago*: Keep unused ComfyUI workflow branches dormant until they are needed.\n- [**Comfyui-DHan-Smart-Memory-Override**](https://github.com/DHan315/Comfyui-DHan-Smart-Memory-Override) (⭐0) *pushed 5 hours ago*: Manual Smart Memory control nodes for ComfyUI.\n- [**Comfyui-DHan-InlineImage**](https://github.com/DHan315/Comfyui-DHan-InlineImage) (⭐0) *pushed 5 hours ago*: Inline image preview, transform, and mask painting node for ComfyUI.\n- [**Comfyui-DHan-MaskingADV**](https://github.com/DHan315/Comfyui-DHan-MaskingADV) (⭐0) *pushed 5 hours ago*: Advanced image masking and editing node for ComfyUI.\n- [**Comfyui-DHan-Composite**](https://github.com/DHan315/Comfyui-DHan-Composite) (⭐0) *pushed 5 hours ago*: Lightweight model-agnostic compositor for preserving source regions and blending generated edits in ComfyUI.\n- [**KIE.ai Nodes Next**](https://github.com/felipederosilva/ComfyUI-KIE-Nodes-Next) (⭐0) *pushed 5 hours ago*: Individual KIE.ai model nodes for ComfyUI with live catalog sync, one-time credentials, and native media I/O.\n- [**ComfyUI-IntoTheLatent-Utils**](https://github.com/Into-The-Latent/ComfyUI-IntoTheLatent-Utils) (⭐2) *pushed 6 hours ago*: ComfyUI utility nodes by Into The Latent.\n- [**RandomLoRALoader**](https://github.com/shin131002/RandomLoRALoader) (⭐2) *pushed 6 hours ago*: A ComfyUI custom node for randomly selecting and applying LoRAs from multiple folders with support for trigger words, sample prompts, and strength randomization.\n- [**ComfyUI-SongLRC**](https://github.com/TheAwaken1/ComfyUI-SongLRC) (⭐4) *pushed 6 hours ago*: Timed .lrc lyrics for generated songs, saved beside the audio, with a player that highlights each line as it is sung.\n- [**GENKAI Nodes**](https://github.com/GENKAIx/Genkai-ComfyUI-Nodes) (⭐9) *pushed 6 hours ago*: PromptSync video tools, MiniMax H3 media references, prompt utilities, and video comparison nodes for ComfyUI.\n- [**ComfyUI Anima Remap**](https://github.com/shin131002/ComfyUI-Anima-Remap) (⭐10) *pushed 6 hours ago*: Use LoRAs, model merges and ControlNets (LLLite/VACE) across Anima generations (Anima, 2.9B, 3.8B/Pro52 and beyond) with automatic block-index remapping\n- [**ComfyUI-ASASR**](https://github.com/claussteinmassl/ComfyUI-ASASR) (⭐0) *pushed 6 hours ago*: ASASR 4x diffusion super-resolution (FLUX.1-dev dual-LoRA) for ComfyUI, with native fp8/GGUF support. Non-commercial (CC-BY-NC-4.0 weights).\n- [**Anymatix**](https://github.com/Anymatix/anymatix-comfy-nodes) (⭐0) *pushed 6 hours ago*: The nodes Anymatix runs on: URL-addressed model loaders that download what a workflow asks for, plus CLIPSeg, masking, SAM2 coordinates and the save nodes Anymatix reads its results from.\n- [**comfyui-Karga_RemoteWorkflows**](https://github.com/kapakahi/comfyui-Karga_RemoteWorkflows) (⭐0) *pushed 7 hours ago*: A stan","projects_url":"https://awesome.ecosyste.ms/api/v1/lists/jalberty2018%2Fawesome-comfyui/projects"}