๐ฌTechnical Deep Dive
Full Specifications [+]
Quick Commands
git clone https://github.com/anil-matcha/seedance2-comfyui โ๏ธ Nexus Index V2.0
๐ฌ Index Insight
FNI V2.0 for Seedance2 Comfyui: Semantic (S:50), Authority (A:0), Popularity (P:51), Recency (R:97), Quality (Q:70).
Verification Authority
๐ What's Next?
Technical Deep Dive
Seedance 2.0 ComfyUI Nodes
ComfyUI custom nodes for Seedance 2.0 โ the state-of-the-art video generation model by ByteDance. Generate stunning AI videos directly inside ComfyUI using the muapi.ai API. If you wish to check the api documentation check this Seedance 2.0 api
What is Seedance 2.0?
Seedance 2.0 is ByteDance's latest video generation model, capable of producing high-quality, photorealistic videos from text prompts or reference images. It supports:
- Text-to-Video โ generate video from a text description
- Image-to-Video โ animate up to 9 reference images with motion guidance
- Omni Reference โ combine images, video clips, and audio as multi-modal reference inputs
- Video Extend โ seamlessly extend any generated video
- Consistent Character โ generate a 4K multi-panel character sheet from reference photos; use
@character:<id>inline in any prompt, or wire the sheet image directly into Consistent Character Video for tighter face fidelity
Nodes
| Node | Description |
|---|---|
| ๐ Seedance 2.0 API Key | Set your key once โ wire to all nodes |
| ๐ฑ Seedance 2.0 Text-to-Video | Generate video from a text prompt |
| ๐ฑ Seedance 2.0 Image-to-Video | Animate up to 9 reference images |
| ๐ฑ Seedance 2.0 Omni Reference | Multi-modal: combine images, video clips, and audio |
| ๐ฑ Seedance 2.0 Consistent Character | Generate a 4K character sheet from 1โ3 reference photos |
| ๐ฑ Seedance 2.0 Consistent Character Video | Animate a scene with locked character identity from a sheet |
| ๐ฑ Seedance 2.0 Extend | Extend a previously generated video |
| ๐ฑ Seedance 2.0 Save Video | Download URL โ disk + ComfyUI IMAGE frames |
Installation
Via ComfyUI Manager (recommended)
- Open ComfyUI Manager โ 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.txtQuick Start
- Sign up at muapi.ai and go to Dashboard โ API Keys โ Create Key
- Right-click the ComfyUI canvas โ Add Node โ ๐ฑ Seedance 2.0
- Add a ๐ Seedance 2.0 API Key node, paste your key, and wire its output to any generation node
- Write a prompt and hit Queue Prompt
Tip: If you use the MuAPI CLI, run
muapi auth configure --api-key YOUR_KEYonce and all nodes will pick it up automatically โ no need to paste the key anywhere.
Node Reference
๐ Seedance 2.0 API Key
Set your muapi.ai API key once and wire the output to all generation nodes. Alternatively, leave every api_key field blank โ nodes automatically read from ~/.muapi/config.json if you've authenticated via the CLI.
๐ฑ Seedance 2.0 Text-to-Video
Generate a video from a text description.
| Field | Values | Default |
|---|---|---|
api_key |
Optional โ leave blank if using the API Key node or CLI config | โ |
prompt |
Text describing the video | โ |
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 ยท first_frame (IMAGE) ยท request_id
๐ฑ Seedance 2.0 Image-to-Video
Animate reference images into a video. Connect up to 9 images via image_1 โฆ image_9 and reference them in the prompt using @image1 โฆ @image9.
Example prompt:
The cat in @image1 walks gracefully through a sunlit garden.
@image1 transforms into @image2 with a smooth dissolve transition.๐ฑ Seedance 2.0 Omni Reference
Multi-modal video generation that combines images, video clips, and audio clips as reference material alongside a text prompt. Use @image1โฆ@image9, @video1โฆ@video3, and @audio1โฆ@audio3 to reference media in the prompt.
Example prompt:
A person @image1 walking on the beach at sunset, cinematic lighting, with @audio1 as background music.| Field | Values | Default |
|---|---|---|
prompt |
Text with optional @imageN, @videoN, @audioN references |
โ |
aspect_ratio |
21:9 / 16:9 / 4:3 / 1:1 / 3:4 / 9:16 | 16:9 |
duration |
4 โ 15 seconds (integer) | 5 |
image_1 โฆ image_9 |
Optional โ ComfyUI IMAGE tensors (auto-uploaded) | โ |
video_url_1 โฆ video_url_3 |
Optional โ MP4 URL (max 15s each) | โ |
audio_url_1 โฆ audio_url_3 |
Optional โ MP3/WAV URL (total max 15s) | โ |
Outputs: video_url ยท first_frame (IMAGE) ยท request_id
๐ฑ Seedance 2.0 Consistent Character
Generate a 4K / 21:9 multi-panel character sheet (front, back, side profile, action pose, facial expressions, accessories) from 1โ3 reference photos of a real person.
| Field | Description |
|---|---|
image_1 โฆ image_3 |
Reference photos of the person (at least 1 required; clear frontal/3-4 angle shots work best) |
outfit_description |
Describe the desired outfit/style for the character |
Outputs:
| Output | Type | Description |
|---|---|---|
sheet_image |
IMAGE | Character sheet as a ComfyUI tensor โ wire directly into Consistent Character Video |
sheet_url |
STRING | CDN URL of the character sheet image |
character_id |
STRING | request_id of this generation โ use as @character:<id> in T2V/I2V/Omni prompts |
Recommended workflow โ wire sheet_image into Consistent Character Video:
[LoadImage] โโโ [๐ฑ Consistent Character] โโ(sheet_image)โโโ [๐ฑ Consistent Character Video]
[outfit_description] (sheet_url) [scene prompt]Alternative โ use @character:<id> in any prompt (simpler but looser face fidelity):
[๐ฑ Consistent Character] character_id โโโ (paste into prompt) โโโ [๐ฑ Text-to-Video]
T2V prompt: "@character:{character_id} rides a motorcycle through a neon-lit city at night"๐ฑ Seedance 2.0 Consistent Character Video
Generate a video scene with locked character identity. Anchors on the character sheet image as @image1 for maximum face/identity preservation.
Connect sheet_image (or paste sheet_url) from the Consistent Character node.
| Field | Description |
|---|---|
prompt |
Scene description. @image1 refers to the character sheet and is auto-prepended if omitted. |
sheet_image |
IMAGE tensor from Consistent Character (preferred) |
sheet_url |
Paste the sheet URL if you don't have the tensor |
scene_image_2, scene_image_3 |
Optional extra scene/background images (referenced as @image2, @image3) |
aspect_ratio |
16:9 / 9:16 / 4:3 / 3:4 |
quality |
basic / high |
duration |
5 / 10 / 15 seconds |
Outputs: video_url ยท first_frame (IMAGE) ยท request_id
Example prompt:
@image1 walks through a rain-soaked neon city, cinematic slow motion๐ฑ Seedance 2.0 Extend
Continue any completed Seedance 2.0 video. Connect the request_id output from a generation node.
| Field | Description |
|---|---|
request_id |
From a completed T2V or I2V generation |
prompt |
Optional โ guide the continuation |
quality |
basic / high |
duration |
5 / 10 / 15 seconds to add |
๐ฑ 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 other nodes (preview, VHS, upscale, etc.).
Example Workflows
Load any .json file from this repo via File โ Load in ComfyUI.
| File | Description |
|---|---|
Seedance2_T2V_Example.json |
Basic text-to-video generation |
Seedance2_ConsistentCharacter_Example.json |
Full consistent character workflow: reference photo โ character sheet โ video |
Text-to-Video:
[๐ API Key] โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ
[๐ฑ Text-to-Video] โ video_url โ [๐ฑ Save Video] โ frames โ [Preview Image]Consistent Character:
[๐ API Key] โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ
[LoadImage] โ [๐ฑ Consistent Character] โ sheet_image โ [๐ฑ Consistent Character Video] โ [๐ฑ Save Video]
[outfit_description] โ [scene prompt]
[Preview Image] โ
(character sheet) [Preview Image]
(first frame)API
This node pack uses the muapi.ai API under the hood:
- T2V:
POST https://api.muapi.ai/api/v1/seedance-v2.0-t2v - I2V:
POST https://api.muapi.ai/api/v1/seedance-v2.0-i2v - Omni:
POST https://api.muapi.ai/api/v1/seedance-2.0-omni-reference - Character:
POST https://api.muapi.ai/api/v1/seedance-2-character - Extend:
POST https://api.muapi.ai/api/v1/seedance-v2.0-extend - Poll:
GET https://api.muapi.ai/api/v1/predictions/{id}/result - Upload:
POST https://api.muapi.ai/api/v1/upload_file
Authentication is a single x-api-key header โ no session tokens required.
Requirements
- Python โฅ 3.8
requestsโฅ 2.28 ยทPillowโฅ 9.0 ยทnumpyโฅ 1.23 ยทtorchโฅ 2.0 ยทopencv-pythonโฅ 4.7
Want More Models?
This repo is focused on Seedance 2.0 only. If you need access to 100+ models โ Kling, Veo3, Flux, HiDream, GPT-image-1.5, Imagen4, Wan, lipsync, audio, image enhancement and more โ check out the full MuAPI ComfyUI node pack:
SamurAIGPT/muapi-comfyui โ ComfyUI nodes for every muapi.ai model in one place.
License
MIT ยฉ 2026
๐ Quick Start
cd ComfyUI/custom_nodes
git clone https://github.com/Anil-matcha/seedance2-comfyui
pip install -r seedance2-comfyui/requirements.txtโ ๏ธ Incomplete Data
Some information about this model is not available. Use with Caution - Verify details from the original source before relying on this data.
View Original Source โ๐ Limitations & Considerations
- โข Benchmark scores may vary based on evaluation methodology and hardware configuration.
- โข VRAM requirements are estimates; actual usage depends on quantization and batch size.
- โข FNI scores are relative rankings and may change as new models are added.
- โ License Unknown: Verify licensing terms before commercial use.
AI Summary: Based on GitHub metadata. Not a recommendation.
๐ก๏ธ Model Transparency Report
Technical metadata sourced from upstream repositories.
๐ Identity & Source
- id
- gh-model--anil-matcha--seedance2-comfyui
- slug
- anil-matcha--seedance2-comfyui
- source
- github
- author
- Anil Matcha
- license
- MIT
- tags
- ai, ai-video, bytedance, comfyui, comfyui-nodes, image-to-video, muapi, seedance, seedance2, text-to-video, video-generation, ai-video-generation, comfyui-custom-nodes, deep-learning, generative-ai, python, stable-diffusion, video-ai, video-synthesis, video-extend
โ๏ธ Technical Specs
- architecture
- null
- params billions
- null
- context length
- null
- pipeline tag
- text-to-image
๐ Engagement & Metrics
- downloads
- 0
- stars
- 0
- forks
- 0
Data indexed from public sources. Updated daily.