CogVideoX
Open text-to-video and image-to-video models from Zhipu AI / Tsinghua.
- Star 数
- 13.1K
- Fork 数
- 1.4K
- 未关闭 Issue
- 115
- 最近提交
- 2025-11-04
数据来自 GitHub API · 更新于 2026-10-15
CogVideoX 是什么？
CogVideoX is a family of open video models (2B and 5B, plus image-to-video variants) that run in Diffusers. With CPU offloading and quantization the smaller models fit consumer GPUs.
主要功能
- Text-to-video, image-to-video and video-to-video
- Diffusers pipelines with memory optimizations
- LoRA fine-tuning scripts
系统要求
- 平台
- Linux · Windows
- 显卡
- NVIDIA
- 显存
- ~12–24 GB depending on model and optimizations (see the README table)
如何安装 CogVideoX
根据项目 README 整理。开源项目更新很快，请以 GitHub 页面上的最新说明为准。
Diffusers
- 1Install Diffusers.
pip install --upgrade diffusers transformers accelerate imageio-ffmpeg - 2Generate a clip in Python.
import torch from diffusers import CogVideoXPipeline from diffusers.utils import export_to_video pipe = CogVideoXPipeline.from_pretrained("THUDM/CogVideoX-5b", torch_dtype=torch.bfloat16) pipe.enable_model_cpu_offload() video = pipe(prompt="A panda playing guitar in a bamboo forest", num_frames=49).frames[0] export_to_video(video, "output.mp4", fps=8)
优势
- Runs on consumer GPUs with offloading
- Good Diffusers support
不足
- Short, low-resolution clips
- Weights for some sizes use a custom license
CogVideoX 替代品对比
| 软件 | Star 数 | 许可证 | 平台 | 显存 |
|---|---|---|---|---|
| CogVideoX Open text-to-video and image-to-video models from Zhipu AI / Tsinghua. | 13.1K | Apache-2.0 | ~12–24 GB depending on model and optimizations (see the README table) | |
| Wan 2.2 Alibaba’s open-weight video generation models (text, image and speech to video). | 17.9K | Apache-2.0 | 24 GB for TI2V-5B at 720p; 80 GB-class GPUs (or offloading) for A14B models | |
| LTX-Video Fast, real-time-capable open video generation from Lightricks. | 11.1K | Apache-2.0 | 12 GB+ for smaller variants; more for 13B models | |
| HunyuanVideo Tencent’s 13B-parameter open video foundation model. | 12.6K | Tencent Hunyuan Community License | 45 GB minimum, 60–80 GB recommended for 720p (per README); less with community quantizations | |
| FramePack Long image-to-video generation on laptop GPUs with as little as 6 GB VRAM. | 17.3K | Apache-2.0 | 6 GB minimum | |
| AnimateDiff Animate your Stable Diffusion checkpoints with plug-in motion modules. | 12.3K | Apache-2.0 | 8–12 GB |
相关模型
常见问题
CogVideoX 免费吗？
是的——CogVideoX 是开源软件，采用 Apache-2.0 许可证。商用前请确认软件及模型权重的许可条款。
CogVideoX 支持 Windows、Mac 和 Linux 吗？
CogVideoX 支持：Linux, Windows。
运行 CogVideoX 需要什么配置？
NVIDIA. VRAM: ~12–24 GB depending on model and optimizations (see the README table)
如何安装 CogVideoX？
1. Install Diffusers. 2. Generate a clip in Python.
CogVideoX 有哪些好的替代品？
常见替代品包括 Wan 2.2, LTX-Video, HunyuanVideo, FramePack，详见本页对比表。
可以不安装、在线使用 CogVideoX 吗？
如果没有大显存显卡，AiLoft 可在云端运行 Veo 3.1 和可灵 2.5，在浏览器中生成并对比视频。
没有 24GB 显卡？在线生成 AI 视频
在云端运行 Veo 3.1 和可灵 2.5，并排对比视频，按条付费。