Mochi in ComfyUI

Latest integrated video generation model in ComfyUI

CommonProductVideoVideo GenerationOpen Source Model

Mochi is the latest open-source video generation model launched by Genmo, optimized for ComfyUI to operate effectively even on consumer-grade GPUs. Renowned for its high fidelity animation and excellent prompt adherence, Mochi brings state-of-the-art video generation capabilities to the ComfyUI community. Released under the Apache 2.0 license, this allows developers and creators to freely use, modify, and integrate Mochi without restrictive licensing issues. Mochi can run on consumer-grade GPUs such as the 4090 and supports multiple attention backends in ComfyUI, making it adaptable for VRAM less than 24GB.

- High Fidelity Animation Generation: Mochi is capable of producing high-quality video content with high-fidelity animated performances.
- Excellent Prompt Adherence: Mochi excels in following user prompts
accurately generating the desired video content.
- Open Source with Unrestricted License: Released under the Apache 2.0 license
users can freely use and modify Mochi.
- Suitable for Consumer-Grade GPUs: Mochi can run on consumer-grade GPUs like the 4090
reducing hardware requirements.
- Supports Multiple Attention Backends: Mochi supports various attention backends in ComfyUI to accommodate different VRAM sizes.
- Optimized Storage Requirements: Mochi can operate with less than 24GB of VRAM
making it accessible to more users.

\The target audience for the Mochi model includes video content creators
developers
and AI enthusiasts. For video creators
Mochi offers a powerful tool to generate high-quality video content without the need for expensive professional-grade hardware. For developers
Mochi's open-source nature and flexible licensing allow for easy integration and customization of the model to meet specific needs. AI enthusiasts can also explore and learn about the latest video generation technologies through Mochi.\

A video blogger uses Mochi to generate high-quality video content
enhancing production efficiency.
Game developers utilize Mochi to create game trailers or animations
reducing production costs.
Educators use Mochi to create educational videos that present complex concepts in a more engaging manner.

1. Update to the latest version of ComfyUI.
2. Download the Mochi weights file to the `models/diffusion_models` folder.
3. Ensure that there is a text encoder in the `models/clip` folder.
4. Download the VAE file to `ComfyUI/models/vae`.
5. Find example workflows and start generating videos.

Visit

Mochi in ComfyUI Visit Over Time

Monthly Visits

86071

Bounce Rate

63.93%

Page per Visit

1.7

Visit Duration

00:02:06

Mochi in ComfyUI Visit Trend

Mochi in ComfyUI Visit Geography

Mochi in ComfyUI Traffic Sources

Mochi in ComfyUI Alternatives

CogVideoX1.5-5B-SAT — An open-source video generation model that supports 10-second videos and higher resolutions.

Video•Video Generation•Text to Video

336

CogVideoX-2B — An open-source video generation model designed to create vivid video content.

Video•Video Generation•AI Creation

738

AnimateAnything — Unified controllable video generation method

Video•Video Generation•Animation

126

Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int4 — A code generation model with 1.5 billion parameters from the Qwen2.5-Coder series.

Programming•Code Generation•Code Reasoning

Qwen2.5-Coder-1.5B-Instruct-AWQ — A 1.5 billion parameter code generation model from the Qwen2.5-Coder series.

Programming•Code Generation•Code Reasoning

Qwen2.5-Coder-3B-Instruct-GPTQ-Int8 — The 3B parameter Instruct model from the Qwen2.5-Coder series.

Programming•Code Generation•Code Reasoning

Qwen2.5-Coder-3B-Instruct-GGUF — Qwen2.5-Coder 3B is a parameter-tuned model within the Qwen2.5-Coder series.

Programming•Code Generation•Code Reasoning

Qwen2.5-Coder-32B-Instruct-GPTQ-Int8 — Open-source code generation language model

Programming•Code Generation•Long Text Processing

Qwen2.5-Coder-1.5B-Instruct — This is a 1.5B parameter code generation model in the Qwen2.5-Coder series.

Programming•Code Generation•Code Reasoning

Qwen2.5-Coder-3B-Instruct — Qwen2.5-Coder Series: A 3B parameter instruction-tuned model.

Programming•Code Generation•Code Reasoning

GameGen-X — A diffusion model for generating and controlling open-world game videos.

Programming•Game Generation•Interactive Control

Oasis — Real-time open-world AI model based on Transformer architecture.

Video•Transformer•Real-Time Interaction

324

Decart — The first real-time generative AI open-world model

InternationalSelection•Video Generation•Real-time Interaction

258

MarDini — A self-regressive diffusion model for large-scale video generation.

Video•Video Generation•Self-Regressive

FasterCache — A video diffusion model acceleration tool that generates high-quality video content without the need for training.

Video•Video Generation•Diffusion Models

ComfyUI-MochiWrapper — ComfyUI wrapper for the Mochi video generator

Programming•Video Generation•Mochi Model

258

mochi-1-preview — Genmo's video generation model features high-fidelity motion and strong adherence to prompts.

Video•Video Generation•Open Source

198

genmoai — Open-source video generation model

Video•Video Generation•Artificial Intelligence

120

Allegro — Advanced text-to-video generation model

Video•AI Video Generation•Text to Video

VidPanos — Generate panoramic videos from panning footage shot on mobile devices.

Video•Panoramic Video•Video Generation

150

Movie Gen Bench — Video Generation Evaluation Benchmark

Video•Video Generation•Evaluation Benchmark

LightRAG — A simple and fast retrieval-augmented generation model

Programming•Natural Language Processing•Retrieval-Augmented Generation

150

CogView3-Plus-3B — A text-to-image generation model that supports high-resolution image generation.

Image•Text-to-Image•Image Generation

330

Pyramid Flow — Pyramid Flow: An Efficient Video Generation Modeling Using Flow Matching Techniques

Video•Video Generation•Autoregressive Models

144

AI Hug Video — Generate realistic hug videos using AI technology, bringing warmth to your memories.

Video•Video Generation•Personalization

288

Hailuo AI — Redefining Video Creation

InternationalSelection•Artificial Intelligence•Video Generation

402

Best AI Websites & Tools

Mochi in ComfyUI

Mochi in ComfyUI Visit Over Time

Mochi in ComfyUI Visit Trend

Mochi in ComfyUI Visit Geography

Mochi in ComfyUI Traffic Sources

Mochi in ComfyUI Alternatives

CogVideoX1.5-5B-SAT — An open-source video generation model that supports 10-second videos and higher resolutions.

CogVideoX-2B — An open-source video generation model designed to create vivid video content.

AnimateAnything — Unified controllable video generation method

Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int4 — A code generation model with 1.5 billion parameters from the Qwen2.5-Coder series.

Qwen2.5-Coder-1.5B-Instruct-AWQ — A 1.5 billion parameter code generation model from the Qwen2.5-Coder series.

Qwen2.5-Coder-3B-Instruct-GPTQ-Int8 — The 3B parameter Instruct model from the Qwen2.5-Coder series.

Qwen2.5-Coder-3B-Instruct-GGUF — Qwen2.5-Coder 3B is a parameter-tuned model within the Qwen2.5-Coder series.

Qwen2.5-Coder-32B-Instruct-GPTQ-Int8 — Open-source code generation language model

Qwen2.5-Coder-1.5B-Instruct — This is a 1.5B parameter code generation model in the Qwen2.5-Coder series.

Qwen2.5-Coder-3B-Instruct — Qwen2.5-Coder Series: A 3B parameter instruction-tuned model.

Fashion-VDM — A video diffusion model for virtual try-on.

ReCapture — Generative video camera control from user videos

X-Portrait 2 — Highly expressive portrait animation technology

GameGen-X — A diffusion model for generating and controlling open-world game videos.

Oasis — Real-time open-world AI model based on Transformer architecture.

Decart — The first real-time generative AI open-world model

MarDini — A self-regressive diffusion model for large-scale video generation.

FasterCache — A video diffusion model acceleration tool that generates high-quality video content without the need for training.

ComfyUI-MochiWrapper — ComfyUI wrapper for the Mochi video generator

mochi-1-preview — Genmo's video generation model features high-fidelity motion and strong adherence to prompts.

genmoai — Open-source video generation model

Allegro — Advanced text-to-video generation model

VidPanos — Generate panoramic videos from panning footage shot on mobile devices.

Movie Gen Bench — Video Generation Evaluation Benchmark

LightRAG — A simple and fast retrieval-augmented generation model

CogView3-Plus-3B — A text-to-image generation model that supports high-resolution image generation.

Pyramid Flow — Pyramid Flow: An Efficient Video Generation Modeling Using Flow Matching Techniques

AI Hug Video — Generate realistic hug videos using AI technology, bringing warmth to your memories.

Hailuo AI — Redefining Video Creation