CogVideo supports text to video and image to video generation in its CogVideo and CogVideoX model projects.
Open source
24 alternativesMochi
The Mochi project provides an open-source model for generating videos.
About Mochi
Mochi is the GitHub repository for Mochi 1 preview, an open-source video generation model created by Genmo and released under a permissive Apache 2.0 license. The model is a 10 billion parameter diffusion model built on an Asymmetric Diffusion Transformer (AsymmDiT) architecture, described in the repository as state of the art with high-fidelity motion and strong prompt adherence in preliminary evaluation.
The repository provides installation instructions, weight downloads, a Gradio UI, a command-line demo, and a Python API for programmatic generation. A separate trainer supports LoRA fine-tuning on your own videos. Running the model requires downloading weights locally and installing FFMPEG to turn outputs into videos, and the repository states that fine-tuning can be done on one H100 or A100 80GB GPU.
Key features
- Open-source video generation model under Apache 2.0 license
- 10 billion parameter diffusion model using AsymmDiT architecture
- Gradio UI and CLI demos for local generation
- Python API with configurable resolution, frames and inference steps
- LoRA fine-tuning trainer for custom videos
- Released AsymmVAE compresses video to 12-channel latent space
Best for: Developers and researchers with suitable GPU hardware who want to run or fine-tune an open video generation model locally.
Good for
- Released under a permissive Apache 2.0 license
- Open weights, inference harness and simple composable API
- Supports LoRA fine-tuning on your own videos
Watch out for
- Requires locally downloading model weights and installing FFMPEG
- LoRA fine-tuning needs one H100 or A100 80GB GPU
- Described as a preview model with preliminary evaluation
Mochi at a glance
- Website
- github.com/genmoai/mochi
- 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 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
Mochi alternatives
Tools and sites you could use instead, ranked by how closely they match.
FramePack Studio extends FramePack into a multifunction tool for creating videos.
Open source
24 alternatives
VideoCrafter2 is a video diffusion model project focused on high-quality generation with limited data.
Fllow.ai generates videos using models including Sora, Veo, Hailuo, Wan, Kling, and Seedance through one video platform.
AIFreeVideo generates videos from text or images and advertises free, watermark-free HD downloads.
FreePick
24 alternativesAlign your Latents: High-Resolution Video Synthesis with Latent Diffusion Models.
Popular in AI Video Generators
Well-known listings from the same topic.
Gstory.aigstory.aiDubprodubpro.aiVibesvibes.aiPlask Motionplask.aiPika AIpikaai.orgFaceless Reelsfacelessreels.app
Mochi FAQ
What license does Mochi use?
The model is released under a permissive Apache 2.0 license.
How do I download the model weights?
Use the download_weights.py script, or download the weights directly from Hugging Face or via the provided magnet link.
What hardware is needed for fine-tuning?
The repository states the model can be fine-tuned with LoRA on one H100 or A100 80GB GPU.
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.