Anil MatchaandClaude Opus 4.7
585e75ee45
Sync endpoint lists with current muapi.ai schema (server/data/schema_data.json, 409 models) to support the latest model families: - Kling Omni / o3 / v3.0 4k variants - Seedance-2 family (sd-2-*, sd-2-vip-*, fast variants, first-last-frame, omni-reference, character) - Wan 2.7 image/video edit + pro variants - Veo-4 + Veo 3.1 lite - Midjourney v7 / v8 / niji - Nano-banana 2 (+edit), Qwen image 2.0 (+pro/+edit) - Pixverse v6 (t2v/i2v/transition/extend) - Vidu Q2 pro/turbo, Q3 pro/turbo (+first-last-frames) - LTX 2.3 t2v/i2v/extend/lipsync - OpenAI Sora-2 standard t2v/i2v - Happy Horse 1 (720p/1080p) - Higgsfield hf-soul / hf-dop - GPT-Image 2 t2i/i2i - Flux-2 Klein turbo + LoRA variants - Suno add-instrumental/add-vocals/generate-mashup/generate-sounds - Meshy-6 and Tripo3D variants (via new Image-to-3D node) - Many V2V utilities (ai-captions, autocrop, video-combiner, luma reframe/modify, runway act-two/aleph, remix-video, kling motion-control) Heuristic updates so payloads use the right input field: - T2I width/height heuristic: + sdxl-image, perfect-pony-xl, neta-lumina - I2I images_list heuristic: + nano-banana, qwen-image-edit, openai-sora, kling-o3 - I2V images_list heuristic: + sd-2-, veo-4, happy-horse, kling-v3.0-omni, kling-v3.0-4k, openai-sora, nano-banana New 🧊 MuAPIImageTo3D node covers all Meshy-6 / Tripo3D endpoints with auto-routing of single-image vs multi/multiview inputs. Final counts: T2I 64, I2I 57, T2V 73, I2V 109, Extend 12, Enhance 14, VideoEdit 43, Lipsync 12, Audio 14, Image-to-3D 9. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
MuAPI ComfyUI Nodes
The ultimate ComfyUI node pack for AI video, image, audio and enhancement — powered by muapi.ai. Run 100+ state-of-the-art AI models inside ComfyUI with a single API key.
What is MuAPI?
MuAPI is a generative media API aggregator giving you access to 100+ cutting-edge models: Seedance 2.0, Kling, Veo3, Flux, HiDream, GPT-image-1.5, Imagen4, and many more — all through one unified API key.
Nodes (12 total)
| Node | Category | Description |
|---|---|---|
| 🔑 MuAPI API Key | 🎬 MuAPI | Set your key once — wire to all nodes |
| 🎨 MuAPI Text-to-Image | 🎨 MuAPI | Flux, HiDream, GPT-image-1.5, Imagen4, Seedream … |
| 🎨 MuAPI Image-to-Image | 🎨 MuAPI | Flux Kontext, GPT-4o edit, Seededit, Wan edit … |
| 🎬 MuAPI Text-to-Video | 🎬 MuAPI | Seedance, Kling, Veo3, Wan, HunyuanVideo, Grok … |
| 🎬 MuAPI Image-to-Video | 🎬 MuAPI | 25+ I2V models, up to 4 reference images |
| 🎬 MuAPI Extend Video | 🎬 MuAPI | Extend any generation via request_id |
| ✨ MuAPI Image Enhance | ✨ MuAPI | Upscale, bg-remove, face-swap, Ghibli, colorize … |
| 🎬 MuAPI Video Edit | 🎬 MuAPI | Effects, dance, dress-change, upscale, lipsync … |
| 🎬 MuAPI Lipsync | 🎬 MuAPI | Sync.ai, Veed, Creatify |
| 🎵 MuAPI Audio | 🎵 MuAPI | Suno create/remix/extend, mmaudio |
| 🎬 MuAPI Generate (Generic) | 🎬 MuAPI | Any endpoint + raw JSON payload |
| 🎬 MuAPI Save Video | 🎬 MuAPI | Download video → disk + IMAGE frames |
Installation
Via ComfyUI Manager:
- 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
Quick Start
- Get API key at muapi.ai → Dashboard → API Keys
- Right-click canvas → Add Node → 🔑 MuAPI API Key, paste your key
- Wire the
api_keyoutput to any generation node and queue the prompt
Tip: If you use the MuAPI CLI, run
muapi auth configure --api-key YOUR_KEYonce and all nodes pick it up automatically — no need to paste the key anywhere.
Generic Node
Call any muapi endpoint with raw JSON. Use __file_1__ … __file_4__ placeholders for auto-uploaded images:
{
"prompt": "The character in @image1 runs through a forest",
"images_list": ["__file_1__"],
"aspect_ratio": "16:9",
"quality": "basic",
"duration": 5
}
Supported Models (selected)
T2V: seedance-v2.0-t2v · kling-v2.6-pro-t2v · veo3.1-text-to-video · wan2.5-text-to-video · hunyuan-text-to-video · minimax-hailuo-02-pro-t2v · grok-imagine-text-to-video
I2V: seedance-v2.0-i2v · seedance-2.0-new-omni · kling-v2.6-pro-i2v · veo3.1-image-to-video · wan2.5-image-to-video · hunyuan-image-to-video
T2I: flux-dev-image · flux-2-pro · flux-kontext-max-t2i · hidream_i1_full_image · gpt4o-text-to-image · google-imagen4-ultra · seedream-5.0 · hunyuan-image-3.0
Enhance: ai-image-upscale · topaz-image-upscale · ai-background-remover · ai-ghibli-style · ai-color-photo · ai-object-eraser
See the full API docs for 100+ endpoints.
License
MIT © 2026