{"id":42481680,"url":"https://github.com/martin-rizzo/ComfyUI-ZImagePowerNodes","last_synced_at":"2026-02-07T20:00:32.229Z","repository":{"id":333212657,"uuid":"1135843016","full_name":"martin-rizzo/ComfyUI-ZImagePowerNodes","owner":"martin-rizzo","description":"A set of ComfyUI nodes designed and fine-tuned specifically for the Z-Image model.","archived":false,"fork":false,"pushed_at":"2026-02-02T00:18:31.000Z","size":793,"stargazers_count":102,"open_issues_count":4,"forks_count":7,"subscribers_count":1,"default_branch":"master","last_synced_at":"2026-02-02T10:18:20.318Z","etag":null,"topics":["comfy-nodes","comfyui","comfyui-nodes","image-generation","text2image","txt2img","z-image","z-image-turbo"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/martin-rizzo.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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,"dco":null,"cla":null}},"created_at":"2026-01-16T17:09:35.000Z","updated_at":"2026-02-02T09:47:45.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/martin-rizzo/ComfyUI-ZImagePowerNodes","commit_stats":null,"previous_names":["martin-rizzo/comfyui-zimagepowernodes"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/martin-rizzo/ComfyUI-ZImagePowerNodes","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/martin-rizzo%2FComfyUI-ZImagePowerNodes","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/martin-rizzo%2FComfyUI-ZImagePowerNodes/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/martin-rizzo%2FComfyUI-ZImagePowerNodes/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/martin-rizzo%2FComfyUI-ZImagePowerNodes/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/martin-rizzo","download_url":"https://codeload.github.com/martin-rizzo/ComfyUI-ZImagePowerNodes/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/martin-rizzo%2FComfyUI-ZImagePowerNodes/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29206797,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-07T17:44:10.191Z","status":"ssl_error","status_checked_at":"2026-02-07T17:44:07.936Z","response_time":63,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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"}},"keywords":["comfy-nodes","comfyui","comfyui-nodes","image-generation","text2image","txt2img","z-image","z-image-turbo"],"created_at":"2026-01-28T11:00:24.072Z","updated_at":"2026-02-07T20:00:32.212Z","avatar_url":"https://github.com/martin-rizzo.png","language":"Python","funding_links":["https://ko-fi.com/martinrizzo","https://github.com/sponsors/martin-rizzo"],"categories":["Workflows pushed today"],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n\n# Z-Image Power Nodes \u003cbr\u003e\u003csub\u003e\u003csup\u003e\u003ci\u003ePushing the best image generation model to its limits!\u003c/i\u003e\u003c/sup\u003e\u003c/sub\u003e\n[![Platform](https://img.shields.io/badge/platform%3A-ComfyUI-007BFF)](#)\n[![License](https://img.shields.io/github/license/martin-rizzo/ComfyUI-ZImagePowerNodes?label=license%3A\u0026color=28A745)](#)\n[![Version](https://img.shields.io/github/v/tag/martin-rizzo/ComfyUI-ZImagePowerNodes?label=version%3A\u0026color=D07250)](#)\n[![Last](https://img.shields.io/github/last-commit/martin-rizzo/ComfyUI-ZImagePowerNodes?label=last%20commit%3A)](#)\n\n\u003cimg src=\"banner_readme.jpg\" width=\"66%\"\u003e\u003c/img\u003e\n\n\u003c/div\u003e\n\n**ComfyUI-ZImagePowerNodes** is a collection of custom nodes designed and refined specifically for the [Z-Image model](https://github.com/Tongyi-MAI/Z-Image). They are based on some ideas and discoveries I made while developing the [Amazing Z-Image Workflow](https://github.com/martin-rizzo/AmazingZImageWorkflow).\n\n\n## Table of Contents\n1. [Nodes](#nodes)\n2. [Examples](#examples)\n3. [Installation](#installation)\n4. [Recommended Checkpoints](#recommended-checkpoints)\n5. [❤️ Support my work](#%EF%B8%8F-support-my-work)\n6. [License](#license)\n\n## Nodes\n\n### ⚡ ZSampler Turbo\n * A specialized sampler designed to divide the denoising process into three stages: composition, details, and refinement. It maintains image stability between 4 and 9 steps and achieves sufficient quality and detail starting from step 7, eliminating the need for further refining or post-processing. \\\n   **[\"ZSampler Turbo\" node documentation](docs/zsampler_turbo.md)**.\n\n### ⚡ Style \u0026 Prompt Encoder\n * Applies a selected visual styles to the prompt and encodes them using a text-encoder model (clip). Enables generating images that follow the desired aesthetic while guiding the diffusion process. \\\n   **[\"Style Prompt Encoder\" node documentation](docs/style_prompt_encoder.md)**\n\n### ⚡ Style String Injector\n * Seamlessly integrates a chosen style into your prompt text. It accepts a string as input and modifies it based on the selected style. \\\n   **[\"Style String Injector\" node documentation](docs/style_string_injector.md)**\n\n### ⚡ Save Image\n * Saves generated images with the option to embed CivitAI-compatible metadata, making it easy to share generation parameters through that platform. \\\n   **[\"Save Image\" node documentation](docs/save_image.md)**.\n\n### ⚡ Empty Z-Image Latent Image\n * Creates an empty latent image of the appropriate size for Z-Image, selecting aspect ratio, scale, and orientation.  \\\n   **[\"Empty Z-Image Latent Image\" node documentation](docs/empty_zimage_latent_image.md)**.\n\n### 💀 ~~Photo-Style Prompt Encoder~~\n * Deprecated, use \"Style \u0026 Prompt Encoder\" node.\n\n### 💀 ~~Illustration-Style Prompt Encoder~~\n * Deprecated, use \"Style \u0026 Prompt Encoder\" node.\n\n\n\n## Examples\n\nA few example workflows demonstrating basic usage of these nodes can be found in the **[/workflows](/workflows)** directory.\n\nAnd hundreds of images generated with Z-Image model and the Power Nodes are available on the **[Z-Image Power Nodes page on CivitAI](https://civitai.com/models/2322533)**. The images posted by me include their prompts and complete generation workflows and you can use them freely as a basis for your own images. Additionally, there are also many users sharing their amazing creations there.\n\n## Installation\n_Ensure you have the latest version of [ComfyUi](https://github.com/comfyanonymous/ComfyUI)._\n\n### Installation via ComfyUI Manager (Recommended)\n\nThe easiest way to install the nodes is through [ComfyUI-Manager](https://github.com/Comfy-Org/ComfyUI-Manager):\n\n  1. Open ComfyUI and click on the \"Manager\" button to launch the \"ComfyUI Manager Menu\".\n  2. Within the ComfyUI Manager, locate and click on the \"Custom Nodes Manager\" button.\n  3. In the search bar, type \"Z-Image Power Nodes\".\n  4. Select the option from the search results and click the \"Install\" button.\n  5. Restart ComfyUI to ensure the changes take effect.\n\n### Manual Installation\n\n\u003cdetails\u003e\n\u003csummary\u003e🛠️ Manual installation instructions. (expand for details)\u003c/summary\u003e\n.\n\n1. Open your preferred terminal application.\n2. Navigate to your ComfyUI directory:\n   ```bash\n   cd \u003cyour_comfyui_directory\u003e\n   ```\n3. Move into the **custom_nodes** folder and clone the repository:\n   ```bash\n   cd custom_nodes\n   git clone https://github.com/martin-rizzo/ComfyUI-ZImagePowerNodes.git\n   ```\n\u003c/details\u003e\n\n### Windows Portable Installation\n\n\u003cdetails\u003e\n\u003csummary\u003e🛠️ Windows portable installation instructions. (expand for details)\u003c/summary\u003e\n.\n\n1. Go to where you unpacked **ComfyUI_windows_portable**,  \n   you'll find your `run_nvidia_gpu.bat` file here, confirming the correct location.\n3. Press **CTRL + SHIFT + RightClick** in an empty space and select \"Open PowerShell window here\".\n4. Clone the repository into your custom nodes folder using:\n   ```\n   git clone https://github.com/martin-rizzo/ComfyUI-ZImagePowerNodes .\\ComfyUI\\custom_nodes\\ComfyUI-ZImagePowerNodes\n   ```\n\u003c/details\u003e\n\n\n## Recommended Checkpoints\n\n### GGUF Format\n\n\u003csub\u003eGGUF checkpoints tend to run slightly slower in ComfyUI. However, if you are building a complex workflow that involves other models or using heavy LLMs with ollama, GGUF files can help prevent system freezes and OOM errors during generation, especially when VRAM is limited. For simple image generation workflows, a safetensors file (though heavier) might be preferable. When working with GGUF in Z-Image, from my experience, using the Q5_K_S quantization typically offers the best balance between file size and prompt response. \u003c/sub\u003e\n\nNote: ComfyUI does not natively support GGUF format, so you need to install the [ComfyUI-GGUF](https://github.com/city96/ComfyUI-GGUF) nodes.\n\n - __[z_image_turbo-Q5_K_S.gguf](https://huggingface.co/jayn7/Z-Image-Turbo-GGUF/blob/main/z_image_turbo-Q5_K_S.gguf)__ \u003csub\u003e[5.19 GB]\u003c/sub\u003e\\\n   Local Directory: __`ComfyUI/models/diffusion_models/`__\n - __[Qwen3-4B.i1-Q5_K_S.gguf](https://huggingface.co/mradermacher/Qwen3-4B-i1-GGUF/blob/main/Qwen3-4B.i1-Q5_K_S.gguf)__ \u003csub\u003e[2.82 GB]\u003c/sub\u003e\\\n   Local Directory: __`ComfyUI/models/text_encoders/`__\n - __[ae.safetensors](https://huggingface.co/Comfy-Org/z_image_turbo/blob/main/split_files/vae/ae.safetensors)__ \u003csub\u003e[335 MB]\u003c/sub\u003e\\\n   Local Directory: __`ComfyUI/models/vae/`__\n\n### Safetensors Format\n\n\u003csub\u003eSafetensors files are generally larger, but ComfyUI includes several built-in optimizations to speed up generation even with limited VRAM. It's always a good idea to test the original safetensors checkpoints on your system to see how they perform. However, using safetensors in fp8 format is strongly discouraged as it can significantly reduce quality. If you have an RTX 50 series GPU based on Blackwell architecture, NVFP4 quantized safetensors could be a better choice.\u003c/sub\u003e\n\n - __[z_image_turbo_bf16.safetensors](https://huggingface.co/Comfy-Org/z_image_turbo/blob/main/split_files/diffusion_models/z_image_turbo_bf16.safetensors)__ \u003csub\u003e(12.3 GB)\u003c/sub\u003e\\\n   Local Directory: __`ComfyUI/models/diffusion_models/`__\n - __[qwen_3_4b.safetensors](https://huggingface.co/Comfy-Org/z_image_turbo/blob/main/split_files/text_encoders/qwen_3_4b.safetensors)__ \u003csub\u003e(8.04 GB)\u003c/sub\u003e\\\n   Local Directory: __`ComfyUI/models/text_encoders/`__\n - __[ae.safetensors](https://huggingface.co/Comfy-Org/z_image_turbo/blob/main/split_files/vae/ae.safetensors)__ \u003csub\u003e(335 MB)\u003c/sub\u003e\\\n   Local Directory: __`ComfyUI/models/vae/`__\n\n## ❤️ Support my work\n\nIf you find these nodes useful or it has helped you in your projects, please consider becoming a sponsor. Your support allows me to keep my tools free and accessible for everyone.\n\n- **Ko-fi:** https://ko-fi.com/martinrizzo\n\n\u003c!--\n[![Sponsor](https://img.shields.io/badge/Sponsor-@martin_rizzo-2ea44f?style=for-the-badge\u0026logo=github-sponsors\u0026logoColor=white)](https://github.com/sponsors/martin-rizzo)\n--\u003e\n\n*Every contribution, no matter how small, is greatly appreciated!*\n\n## License\n\nCopyright (c) 2026 Martin Rizzo  \nThis project is licensed under the MIT license.  \nSee the [\"LICENSE\"](LICENSE) file for details.\n  \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmartin-rizzo%2FComfyUI-ZImagePowerNodes","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmartin-rizzo%2FComfyUI-ZImagePowerNodes","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmartin-rizzo%2FComfyUI-ZImagePowerNodes/lists"}