About Mochi 1 (Genmo)
Mochi 1 is an open text-to-video model from Genmo, built on its Asymmetric Diffusion Transformer architecture with about 10 billion parameters. Weights and inference code are released under Apache 2.0, and there is a LoRA fine-tuning trainer. Genmo also runs a free web playground. It is best for researchers and tinkerers who want a permissively licensed model to run or fine-tune.
Specs
| Pricing | Open source |
|---|---|
| Free tier | Free weights (Apache 2.0) and a free playground on genmo.ai |
| Max clip length | |
| Max resolution | 480p |
| Watermark on free plan | |
| Commercial use | Apache 2.0 license |
| Developer API | |
| Open source | Yes |
Last verified 2026-10-23. A dash means we couldn't confirm it from an official source — we leave it blank rather than guess.
Pros
- Permissive Apache 2.0 license
- Native ComfyUI support, including consumer-GPU workflows
- Includes a LoRA fine-tuning trainer for your own videos
Cons
- Reference repo needs about 60GB VRAM on a single GPU (at least one H100 recommended); ComfyUI can run it in under 20GB
- Released as a research preview at 480p only, and Genmo says it handles animated content poorly
- The only public checkpoint is still mochi-1-preview from October 2024
Mochi 1 (Genmo) alternatives
Compare all →Wan (Alibaba)
Open source
Alibaba's Apache-licensed open video models for T2V, I2V, speech and animation
HunyuanVideo
Open source
Tencent's open-weight 8.3B video model that runs on consumer GPUs
LTX Studio
Free plan · from $15/mo
Lightricks' storyboard-to-video studio powered by the open LTX-2.5 model
Pika
Free plan · from $10/mo
Playful multi-model video app with effects, swaps and its own Pika 2.5 model
Adobe Firefly Video
Free plan · from $9.99/mo
Adobe's commercially safe video model plus partner models inside Firefly
Dreamina (Seedance)
Free plan · from $15/mo
CapCut's creative app and home of ByteDance's Seedance video models