ComfyUI Integration

MuAPI provides two ComfyUI custom node packs, letting you run any MuAPI model directly inside ComfyUI workflows.

Repo	Purpose
muapi-comfyui	Full suite — 11 nodes covering all 100+ MuAPI models
seedance2-comfyui	Seedance 2.0 focused — 4 dedicated nodes

muapi-comfyui (Full Suite)

Access every MuAPI model — image, video, audio, enhancement — from a single node pack.

Installation

Via ComfyUI Manager (recommended):

Open ComfyUI Manager → Install via Git URL
Paste: https://github.com/SamurAIGPT/muapi-comfyui
Restart ComfyUI

Manual:

cd ComfyUI/custom_nodes
git clone https://github.com/SamurAIGPT/muapi-comfyui
pip install -r muapi-comfyui/requirements.txt

Nodes

Node	Description
🎨 MuAPI Text-to-Image	Flux, HiDream, GPT-image-1.5, Imagen4, Seedream
🎨 MuAPI Image-to-Image	Flux Kontext, GPT-4o edit, Seededit, Wan edit
🎬 MuAPI Text-to-Video	Seedance, Kling, Veo3, Wan, HunyuanVideo
🎬 MuAPI Image-to-Video	25+ I2V models, up to 4 reference images
🎬 MuAPI Extend Video	Extend any generation via `request_id`
✨ MuAPI Image Enhance	Upscale, bg-remove, face-swap, Ghibli, colorize
🎬 MuAPI Video Edit	Effects, dance, dress-change, lipsync
🎬 MuAPI Lipsync	Sync.ai, Veed, Creatify
🎵 MuAPI Audio	Suno create/remix/extend, mmaudio
🎬 MuAPI Generate	Call any endpoint with raw JSON payload
🎬 MuAPI Save Video	Download video URL → disk + IMAGE frames

Generic Node

The MuAPI Generate node lets you call any MuAPI endpoint with a raw JSON payload. Use __file_1__…__file_4__ placeholders for images — they are automatically uploaded and replaced with CDN URLs before submission.

{
  "prompt": "The character in @image1 runs through a forest",
  "images_list": ["__file_1__"],
  "aspect_ratio": "16:9",
  "quality": "basic",
  "duration": 5
}

seedance2-comfyui (Seedance 2.0 Focused)

A lightweight node pack dedicated to Seedance 2.0 — ByteDance's state-of-the-art video generation model.

Installation

Via ComfyUI Manager (recommended):

Open ComfyUI Manager → Install via Git URL
Paste: https://github.com/Anil-matcha/seedance2-comfyui
Restart ComfyUI

Manual:

cd ComfyUI/custom_nodes
git clone https://github.com/Anil-matcha/seedance2-comfyui
pip install -r seedance2-comfyui/requirements.txt

Nodes

🌱 Seedance 2.0 Text-to-Video

Generate a video from a text description.

Field	Values	Default
`api_key`	Your muapi.ai API key	—
`prompt`	Text describing the video	—
`aspect_ratio`	16:9 / 9:16 / 4:3 / 3:4	16:9
`quality`	basic / high	basic
`duration`	5 / 10 / 15 seconds	5

Outputs: video_url · first_frame (IMAGE) · request_id

🌱 Seedance 2.0 Image-to-Video

Animate up to 9 reference images. Connect images via image_1…image_9 and reference them in the prompt using @image1…@image9.

The cat in @image1 walks gracefully through a sunlit garden.
@image1 transforms into @image2 with a smooth dissolve.

Outputs: video_url · first_frame (IMAGE) · request_id

🌱 Seedance 2.0 Extend

Extend a previously generated video. Connect request_id from any completed generation node.

Field	Description
`request_id`	From a completed T2V or I2V node
`prompt`	Optional — guide the continuation
`quality`	basic / high
`duration`	5 / 10 / 15 seconds to add

🌱 Seedance 2.0 Save Video

Downloads the generated video to ComfyUI's output folder and returns all frames as an IMAGE tensor for use with Preview Image or other nodes.

Quick Start

Sign up at muapi.ai and go to Dashboard → API Keys → Create Key
Install either node pack via ComfyUI Manager
Right-click the canvas → Add Node → find the MuAPI or Seedance 2.0 category
Paste your API key and queue the prompt

Example Workflows

Text-to-Video:

[🌱 Text-to-Video] → video_url → [🌱 Save Video] → frames → [Preview Image]

Image-to-Video:

[Load Image] → image_1 → [🎬 MuAPI Image-to-Video] → video_url → [🎬 MuAPI Save Video]

Enhancement pipeline:

[Load Image] → [✨ MuAPI Image Enhance (bg-remove)] → [✨ MuAPI Image Enhance (upscale)] → [Preview Image]

Requirements

Python ≥ 3.8
requests · Pillow · numpy · torch · opencv-python

For in-canvas video playback, install ComfyUI-VideoHelperSuite.