{"id":23233602,"url":"https://github.com/MinusZoneAI/ComfyUI-CogVideoX-MZ","last_synced_at":"2025-08-19T18:33:52.035Z","repository":{"id":255715914,"uuid":"841977341","full_name":"MinusZoneAI/ComfyUI-CogVideoX-MZ","owner":"MinusZoneAI","description":"CogVideoX-5B 4-bit quantization model","archived":false,"fork":false,"pushed_at":"2024-10-30T10:52:42.000Z","size":2480,"stargazers_count":81,"open_issues_count":22,"forks_count":3,"subscribers_count":1,"default_branch":"main","last_synced_at":"2024-10-30T11:37:34.516Z","etag":null,"topics":["cogvideox","comfyui","comfyui-nodes","dit"],"latest_commit_sha":null,"homepage":"","language":"Python","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/MinusZoneAI.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}},"created_at":"2024-08-13T12:27:40.000Z","updated_at":"2024-10-30T10:52:46.000Z","dependencies_parsed_at":"2024-09-06T21:24:17.518Z","dependency_job_id":null,"html_url":"https://github.com/MinusZoneAI/ComfyUI-CogVideoX-MZ","commit_stats":null,"previous_names":["minuszoneai/comfyui-cogvideox-mz"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MinusZoneAI%2FComfyUI-CogVideoX-MZ","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MinusZoneAI%2FComfyUI-CogVideoX-MZ/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MinusZoneAI%2FComfyUI-CogVideoX-MZ/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MinusZoneAI%2FComfyUI-CogVideoX-MZ/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/MinusZoneAI","download_url":"https://codeload.github.com/MinusZoneAI/ComfyUI-CogVideoX-MZ/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":230367780,"owners_count":18215325,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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":["cogvideox","comfyui","comfyui-nodes","dit"],"created_at":"2024-12-19T03:01:55.458Z","updated_at":"2025-08-19T18:33:52.016Z","avatar_url":"https://github.com/MinusZoneAI.png","language":"Python","funding_links":[],"categories":["Workflows (3395) sorted by GitHub Stars","All Workflows Sorted by GitHub Stars"],"sub_categories":[],"readme":"![image](./examples/workflow_I2V_GGUF_Q4_0.png)\n\n# ComfyUI-CogVideoX-MZ \n\n在 https://github.com/kijai/ComfyUI-CogVideoXWrapper 的基础上增加一个独立的模型加载器和一些其他的功能, 使用前需要先安装ComfyUI-CogVideoXWrapper\n \nBased on https://github.com/kijai/ComfyUI-CogVideoXWrapper add model loader and some other features, you need to install ComfyUI-CogVideoXWrapper before using\n\n## Update - 2024-09-24\n添加vae encode tiling开关, 在16G显存下可以生成1024分辨率的视频不会OOM\n\n(add vae encode tiling switch, can generate 1024 resolution video without OOM on 16G vram)\n\n\n## Update - 2024-09-22\n支持CogVideoX-I2V图生视频, 提供Q4量化模型\n\n(support CogVideoX-I2V image to video, provide Q4 quantization model)\n\n[CogVideoX_5b_I2V_GGUF_Q4_0.safetensors](https://huggingface.co/Kijai/CogVideoX_GGUF/resolve/main/CogVideoX_5b_I2V_GGUF_Q4_0.safetensors) 下载到unet文件夹 (Donwload to unet folder)\n\n工作流在examples\\workflow_I2V_GGUF_Q4_0.png (Workflow in examples\\workflow_I2V_GGUF_Q4_0.png)\n\nPrompt :The girl in the video happily puts on sunglasses.\n\n\nhttps://github.com/user-attachments/assets/3eae12b7-1a2d-40c5-b6fb-10afb1349f4e\n\n\n\n## Update - 2024-09-19\n支持CogVideoX-Fun图生视频, 提供Q4量化模型\n\n(support CogVideoX-Fun image to video, provide Q4 quantization model)\n\n[CogVideoX_Fun_GGUF_Q4_0.safetensors](https://modelscope.cn/models/wailovet/CogVideoX-5b/resolve/master/CogVideoX_5b_fun_GGUF_Q4_0.safetensors) 下载到unet文件夹 (Donwload to unet folder)\n\n工作流在examples\\workflow_FUN_I2V_GGUF_Q4_0.png (Workflow in examples\\workflow_FUN_I2V_GGUF_Q4_0.png)\n\nPrompt :The girl in the video happily puts on sunglasses.\n\nhttps://github.com/user-attachments/assets/32101df0-d50c-404a-a2ea-3ddff0dcc59b\n\n## Update - 2024-09-05\n部分层4位量化模型, 采样方式选择DPM, weight_dtype选择GGUF, cpu_offload不启用分辨率480x720在32帧下占用显存小于8G\n\n(CogVideoX-5B 4-bit quantization model, when using it, the sampling method needs to select DPM, weight_dtype selects GGUF, and cpu_offload is not enabled)\n\n[CogVideoX_5b_GGUF_Q4_0.safetensors](https://modelscope.cn/models/wailovet/CogVideoX-5b/resolve/master/CogVideoX_5b_GGUF_Q4_0.safetensors) 下载到unet文件夹\n\n4位量化工作流在examples\\workflow_GGUF_Q4_0.png\n\n## 使用\nCogVideoX-5B的模型加载器\n\n依赖 https://github.com/kijai/ComfyUI-CogVideoXWrapper\n\n模型下载地址\n\n[CogVideoX_5b_fp8_4em.safetensors](https://modelscope.cn/models/wailovet/CogVideoX-5b/resolve/master/CogVideoX_5b_fp8_4em.safetensors) 下载到unet文件夹 \n\n[diffusion_pytorch_model.safetensors](https://modelscope.cn/models/zhipuai/cogvideox-5b/resolve/master/vae/diffusion_pytorch_model.safetensors) 下载到vae文件夹(记得重命名文件名方便辨认)\n\n[t5xxl_fp8_e4m3fn.safetensors](https://modelscope.cn/models/ai-modelscope/flux_text_encoders/resolve/master/t5xxl_fp8_e4m3fn.safetensors) 下载到clip文件夹(和sd3/flux通用,不需要重复下载)\n\n工作流在examples/*.png\n\n## Usage\n\nCogVideoX-5B model loader\n\nDepends on https://github.com/kijai/ComfyUI-CogVideoXWrapper\n\nModel download address\n\n[CogVideoX_5b_fp8_4em.safetensors](https://modelscope.cn/models/wailovet/CogVideoX-5b/resolve/master/CogVideoX_5b_fp8_4em.safetensors) Download to unet folder\n\n[diffusion_pytorch_model.safetensors](https://modelscope.cn/models/zhipuai/cogvideox-5b/resolve/master/vae/diffusion_pytorch_model.safetensors) Download to vae folder (remember to rename the file name for easy identification)\n\n[t5xxl_fp8_e4m3fn.safetensors](https://modelscope.cn/models/ai-modelscope/flux_text_encoders/resolve/master/t5xxl_fp8_e4m3fn.safetensors) Download to clip folder (universal with sd3/flux, no need to download repeatedly)\n\nWorkflow in examples/*.png\n\n\n## Credits\n\n- [CogVideo](https://github.com/THUDM/CogVideo)\n- [CogVideoX-Fun](https://github.com/aigc-apps/CogVideoX-Fun)\n- [ComfyUI-CogVideoXWrapper](https://github.com/kijai/ComfyUI-CogVideoXWrapper)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FMinusZoneAI%2FComfyUI-CogVideoX-MZ","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FMinusZoneAI%2FComfyUI-CogVideoX-MZ","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FMinusZoneAI%2FComfyUI-CogVideoX-MZ/lists"}