RepoStepFunStepFunpublished Mar 11, 2025seen 5d

stepfun-ai/ComfyUI-StepVideo

Python

Open original ↗

Captured source

source ↗
published Mar 11, 2025seen 5dcaptured 14hhttp 200method plain

stepfun-ai/ComfyUI-StepVideo

Language: Python

License: MIT

Stars: 43

Forks: 6

Open issues: 3

Created: 2025-03-11T04:12:38Z

Pushed: 2025-03-27T07:52:26Z

Default branch: main

Fork: no

Archived: no

README:

ComfyUI-StepVideo

This repository contains ComfyUI custom nodes for StepVideo.

TI2V

Workflow

[TI2V.json](workflow/TI2V.json) ![TI2V](workflow/TI2V.jpg)

Model Weights

Download the model weights from this link.

Install

1. Install Step-Video-TI2V

2. Install ComfyUI custom nodes for StepVideo

cd ComfyUI/custom_nodes
git clone https://github.com/stepfun-ai/ComfyUI-StepVideo.git

Inference

1. Launch Step-Video-TI2V remote_server

cd Step-Video-TI2V
python api/call_remote_server.py --model_dir where_you_download_dir & ## We assume you have more than 4 GPUs available. This command will return the URL for both the caption API and the VAE API. Please use the returned URL as "remote_server_url" parameter in the "TI2V" node.

2. Launch ComfyUI

cd ComfyUI
python main.py

TI2V_API

Workflow

[TI2V_API.json](workflow/TI2V_API.json) ![TI2V_API](workflow/TI2V_API.jpg)

Usage

api_url: https://api.stepfun.com/v1/video/generations

api_key: get api_key from https://platform.stepfun.com

Todo

  • [x] TI2V node
  • [x] TI2V_API node
  • [ ] T2V node
  • [ ] T2V_API node

Notability

notability 4.0/10

New repo with modest traction