FramePack Studio extends FramePack into a multifunction tool for creating videos.
Open source
24 alternativesTHUDM/CogVideo
CogVideo supports text to video and image to video generation in its CogVideo and CogVideoX model projects.
About THUDM/CogVideo
THUDM/CogVideo is an open-source repository for the CogVideo (ICLR 2023) and CogVideoX series models for text-to-video and image-to-video generation. It includes inference and fine-tuning code using SAT and Diffusers implementations, plus tools for LoRA fine-tuning, DDIM Inverse, prompt optimization, and video captioning with CogVLM2-Caption. The CogVideoX series also supports video continuation.
Online demos are listed for Hugging Face Space and ModelScope Space. Local use requires compatible GPUs, such as GTX 1080TI-class hardware for CogVideoX-2B and RTX 3060-class hardware for CogVideoX-5B, with specific dependency setup.
Key features
- Text-to-video generation with CogVideo and CogVideoX models
- Image-to-video generation using image plus text prompt
- Video continuation task in CogVideoX series
- Inference and fine-tuning via SAT and Diffusers code
- LoRA fine-tuning with reduced GPU memory use
- DDIM Inverse support in CogVideoX-5B and CogVideoX1.5-5B
Best for: Developers and researchers with Python and GPU resources who want to run or fine-tune open-source video generation models.
Good for
- Open source with SAT and Diffusers code and fine-tuning tools
- Supports text-to-video, image-to-video, and video continuation
- Lists online demos on Hugging Face Space and ModelScope Space
Watch out for
- Local use requires compatible GPUs and specific dependency setup
- Some releases lag across implementations, such as Diffusers adaptation for CogVideoX1.5
- Larger commercial models are accessed separately via QingYing and API Platform
THUDM/CogVideo at a glance
- Website
- github.com/THUDM/CogVideo
- Category
- AI & Machine Learning › AI Video Generators
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
THUDM/CogVideo alternatives
Tools and sites you could use instead, ranked by how closely they match.
VideoCrafter2 is a video diffusion model project focused on high-quality generation with limited data.
Genmo develops video generation models and offers video creation with Mochi.
Open source
24 alternatives
Pika provides video and image generation tools, with model versions and templates listed on its creative platform.
fal provides an API for integrating the Seedance 2.0 video generation model.
The Video Generation Leaderboard compares text to video models using sample videos and rankings.
Popular in AI Video Generators
Well-known listings from the same topic.
AIFreeVideoaifreevideo.comGstory.aigstory.aiDubprodubpro.aiVibesvibes.aiPlask Motionplask.aiFaceless Reelsfacelessreels.app
THUDM/CogVideo FAQ
What tasks do CogVideoX models support?
Text-to-video generation, video continuation, and image-to-video generation.
What hardware is needed to run the models locally?
CogVideoX-2B runs on older GPUs like GTX 1080TI, and CogVideoX-5B on desktop GPUs like RTX 3060, with required dependencies installed.
Where can I try CogVideoX-5B without installing it?
Online via Hugging Face Space or ModelScope Space.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.