Vimoo-1.0-ComfyUI

Vimoo-1.0-ComfyUI contains the ComfyUI weights for Vimoo-1.0 T2V and I2V (≈11.7B each), plus Vimoo-1.0 T2V Distilled and I2V Distilled. The models share the text encoders and VAE. Vimoo-1.0-Lite models are in Vimoo-1.0-Lite-ComfyUI. Use it with ComfyUI-Vimoo, which provides the nodes and workflow templates.

See the Vimoo 1.0 repository for the model family, online API, system overview, architecture and evaluation.

🔥 News

[2026-10] Release Vimoo 1.0: T2V / I2V models, Diffusers inference examples and ComfyUI workflows.

🎬 Showcase

🚀 Quick Start

Requirements

ComfyUI: 0.34.0 or later.
Python: 3.10 or later; install dependencies in the environment that launches ComfyUI.
PyTorch: 2.9.0 or later, using a CUDA-enabled build compatible with your GPU and driver. Choose the build with the PyTorch installation selector.
Hardware: an NVIDIA CUDA GPU.
Attention: all supplied workflows default to PyTorch SDPA (attention=pytorch), with no additional attention package. Install FA2, FA3, FA4 or SageAttention only when selecting it in Vimoo Performance Options; see performance options.

Use separate environments for ComfyUI and the Diffusers examples; their Transformers dependencies differ. ComfyUI manages its Torch installation.

Install the nodes

Install ComfyUI, then run these commands from its root directory:

git clone https://github.com/Vimoo-AI/ComfyUI-Vimoo custom_nodes/ComfyUI-Vimoo
python -m pip install -r custom_nodes/ComfyUI-Vimoo/requirements.txt

Restart ComfyUI and refresh the browser to load the Vimoo nodes and templates.

Download weights

Run these commands from the ComfyUI root directory. Install the Hugging Face CLI with python -m pip install -U huggingface_hub if hf is not available. Every workflow needs the shared text encoders and VAE; I2V workflows also use the SigLIP vision encoder:

hf download Vimoo-AI/Vimoo-1.0-ComfyUI \
  text_encoders/vimoo_v1_qwen2_5_vl_7b_bf16.safetensors \
  text_encoders/vimoo_v1_glyph_byt5_fp32.safetensors \
  clip_vision/vimoo_v1_siglip_so400m_fp16.safetensors \
  vae/vimoo_v1_wan22_ti2v_vae_fp32.safetensors \
  --local-dir models

Then download the files for your model in the same way:

Model	Files
T2V	`diffusion_models/vimoo_v1_t2v_bf16.safetensors` `diffusion_models/vimoo_v1_t2v_bf16.safetensors.vimoo.json`
I2V	`diffusion_models/vimoo_v1_i2v_bf16.safetensors` `diffusion_models/vimoo_v1_i2v_bf16.safetensors.vimoo.json`
T2V Distilled	`diffusion_models/vimoo_v1_t2v_distilled_bf16.safetensors` `diffusion_models/vimoo_v1_t2v_distilled_bf16.safetensors.vimoo.json` `loras/vimoo_v1_t2v_distilled_lora_bf16.safetensors` `loras/vimoo_v1_t2v_distilled_lora_bf16.safetensors.json`
I2V Distilled	`diffusion_models/vimoo_v1_i2v_distilled_bf16.safetensors` `diffusion_models/vimoo_v1_i2v_distilled_bf16.safetensors.vimoo.json` `loras/vimoo_v1_i2v_distilled_lora_bf16.safetensors` `loras/vimoo_v1_i2v_distilled_lora_bf16.safetensors.json`

For example, for Vimoo-1.0 T2V:

hf download Vimoo-AI/Vimoo-1.0-ComfyUI \
  diffusion_models/vimoo_v1_t2v_bf16.safetensors \
  diffusion_models/vimoo_v1_t2v_bf16.safetensors.vimoo.json \
  --local-dir models

The downloaded files use this layout under ComfyUI/models/:

ComfyUI/models/
├── diffusion_models/
│   ├── vimoo_v1_t2v_bf16.safetensors
│   ├── vimoo_v1_t2v_bf16.safetensors.vimoo.json
│   ├── vimoo_v1_i2v_bf16.safetensors
│   ├── vimoo_v1_i2v_bf16.safetensors.vimoo.json
│   ├── vimoo_v1_t2v_distilled_bf16.safetensors
│   ├── vimoo_v1_t2v_distilled_bf16.safetensors.vimoo.json
│   ├── vimoo_v1_i2v_distilled_bf16.safetensors
│   └── vimoo_v1_i2v_distilled_bf16.safetensors.vimoo.json
├── text_encoders/
│   ├── vimoo_v1_qwen2_5_vl_7b_bf16.safetensors
│   └── vimoo_v1_glyph_byt5_fp32.safetensors
├── clip_vision/
│   └── vimoo_v1_siglip_so400m_fp16.safetensors
├── vae/
│   └── vimoo_v1_wan22_ti2v_vae_fp32.safetensors
└── loras/
    ├── vimoo_v1_t2v_distilled_lora_bf16.safetensors
    ├── vimoo_v1_t2v_distilled_lora_bf16.safetensors.json
    ├── vimoo_v1_i2v_distilled_lora_bf16.safetensors
    └── vimoo_v1_i2v_distilled_lora_bf16.safetensors.json

Keep each .vimoo.json and .json file next to its weights. The nodes read the supported tasks, the matching base checkpoint and the sampling settings from them.

Generate video

Open the workflow for your model from ComfyUI's template browser, or drag its JSON from the models and workflows table onto the canvas.
Select the checkpoint in Vimoo Model Loader. For a distilled workflow, check its adapter inside the generation subgraph. Keep the saved node connections and defaults.
Edit the prompt. For I2V, upload a reference image in Vimoo Load Image; it is scaled and center-cropped to the output size.
Click Queue. Videos are saved to ComfyUI/output/.

T2V and I2V use separate templates and checkpoints.

📋 Models and Workflows

Model	Checkpoint	LoRA	Workflow
T2V	`vimoo_v1_t2v_bf16.safetensors`	None	vimoo_v1_t2v.json
I2V	`vimoo_v1_i2v_bf16.safetensors`	None	vimoo_v1_i2v.json
T2V Distilled	`vimoo_v1_t2v_distilled_bf16.safetensors`	`vimoo_v1_t2v_distilled_lora_bf16.safetensors`	vimoo_v1_t2v_distilled.json
I2V Distilled	`vimoo_v1_i2v_distilled_bf16.safetensors`	`vimoo_v1_i2v_distilled_lora_bf16.safetensors`	vimoo_v1_i2v_distilled.json

Pair each distilled adapter with the checkpoint shown in the table. The Distilled models read their settings from the adapter .json files.

🎛️ Workflow Defaults

The templates provide model loading, performance, generation and video output nodes; I2V adds an image input. Expand the generation subgraph to select supporting encoder, VAE and adapter files. Ordinary models expose steps and text CFG; Distilled models keep their fixed sampling settings.

resolution=auto fits the oriented I2V image ratio to a 1280 × 720 pixel budget, rounding both axes down to multiples of 16. A square image produces 960 × 960; a portrait 9:16 image produces 720 × 1280. Choose manual to enter width and height. T2V defaults to manual 1280 × 720. The initial frame count is 121 at 24 fps.

The Distilled workflows use CFG 1 and only the positive prompt; keep their saved sampling grid and matching adapter metadata. Keep the generation FPS and the video output FPS equal.

Memory, attention and VAE decoding options are described in the ComfyUI-Vimoo README.

📝 Prompting Guide

Use English prompts. The current open-source models have been validated only with English prompts. Generation quality and prompt adherence in other languages have not been validated. We recommend translating prompts into English before generation.

Write clear, detailed prompts. Specific descriptions of the subject, scene, action sequence, and camera movement can help produce results that better match your intent than short, vague prompts. See the Prompt Guide for structure and examples, and focus on relevant, consistent visual details.

The Prompt Guide describes automatic prompt enhancement in the hosted service. Local examples use your input prompt directly; follow the guide's writing structure and examples when preparing prompts.

📜 License

Vimoo model weights and official adapters in this repository are provided under the Apache License 2.0.

Commercial use, modification, and redistribution are permitted under the terms of the license.
Redistribution must include a copy of the license, retain applicable copyright and attribution notices, and identify modified files.
Attribution and third-party component notices are provided in THIRD_PARTY_NOTICES.md. Third-party components remain subject to their own licenses.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including Vimoo-AI/Vimoo-1.0-ComfyUI

Vimoo 1.0

Collection

5 items • Updated 2 days ago • 2