Seedance-2.5-Spicy-API

mcp
Security Audit
Warn
Health Warn
  • License — License: MIT
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 5 GitHub stars
Code Pass
  • Code scan — Scanned 5 files during light audit, no dangerous patterns found
Permissions Pass
  • Permissions — No dangerous permissions requested

No AI report is available for this listing yet.

SUMMARY

Python wrapper for ByteDance's Seedance 2.5 Spicy API — relaxed-moderation flagship tier via MuAPI. Native 4K, 30s clips, Omni Reference, Video Edit/Extend, Motion Control.

README.md

Seedance 2.5 Spicy API: Python Wrapper for ByteDance's Relaxed-Moderation AI Video Generator

Powered by MuAPI

PyPI version
GitHub stars
License: MIT
Python 3.7+

The most comprehensive Python wrapper for the Seedance 2.5 Spicy API (developed by ByteDance), delivered via muapi.ai. Seedance 2.5 Spicy is the relaxed-moderation variant of the Seedance 2.5 flagship model — native 4K, up to 30-second clips, native audio, and precise camera trajectory control, with reduced content-safety filtering and more dramatic, higher-contrast motion than the standard tier.

⚠️ Content policy notice: "Spicy" means reduced automated content-safety filtering, not an anything-goes endpoint. Generated content still must comply with MuAPI's and the underlying provider's terms of service and applicable law. Do not use this API to generate content involving minors, non-consensual imagery, or other prohibited material.

Related Projects

🚀 Why Use Seedance 2.5 Spicy API?

  • Relaxed Content Filtering: Broader creative range than the standard Seedance 2.5 tier, while keeping the same underlying model quality.
  • Native 4K: Photorealistic 4K output on nearly every endpoint (price scales with resolution).
  • Extended Clips: Up to 30-second generations on Omni Reference, First & Last Frame, Video Edit, Video Extend, and Motion Control.
  • Native Audio: Synchronized audio generated alongside the video (toggleable).
  • Draft Mode: Generate a cheap 480p draft first, then finalize the keeper at full resolution without re-submitting the whole prompt.
  • Omni-Reference: Blend up to 30 images, 10 video clips, and 10 audio files into a single guided generation.
  • Motion Control: Recast an existing performance video with new performers while preserving the original motion, choreography, blocking, and camera work.

🌟 Key Features

  • ✅ Text-to-Video: Photorealistic 4K video directly from a text prompt.
  • ✅ Image-to-Video: Animate a single image, with optional first-last frame control.
  • ✅ First & Last Frame: Smooth transition between a start and end image, up to 30s.
  • ✅ Omni-Reference: Multi-modal generation from up to 30 images, 10 videos, and 10 audio references.
  • ✅ Video Edit: Rewrite lighting, style, weather, or elements of an existing video via natural-language instructions.
  • ✅ Video Extend: Generate a cinematic continuation from a video's last frame.
  • ✅ Motion Control: Recast a performance video's performers/environment while preserving motion and camera work.
  • ✅ Draft → Finalize Workflow: Cheap 480p drafts finalized to 1080p+ without resubmitting prompts/media.
  • ✅ File Upload: Upload local images/videos/audio directly via upload_file().

🛠 Installation

Via Pip (Recommended)

pip install seedance-2-5-spicy-api

From Source

git clone https://github.com/Anil-matcha/Seedance-2.5-Spicy-API.git
cd Seedance-2.5-Spicy-API
pip install -r requirements.txt

Configuration

Create a .env file in the root directory and add your MuAPI API key:

MUAPI_API_KEY=your_muapi_api_key_here

🤖 Seedance 2.5 Spicy MCP Server

Use Seedance 2.5 Spicy as an MCP (Model Context Protocol) server so AI assistants (Claude Desktop, Cursor, etc.) can invoke the tools directly.

python3 mcp_server.py

Test with the MCP Inspector:

npx -y @modelcontextprotocol/inspector python3 mcp_server.py

💻 Quick Start (Python)

from seedance_2_5_spicy_api import Seedance25SpicyAPI

api = Seedance25SpicyAPI()

# Text-to-Video (Spicy)
submission = api.text_to_video(
    prompt="A high-contrast, adrenaline-fueled chase through a rain-soaked neon megacity at night, "
           "sparks and shattering glass in slow motion, aggressive handheld camera energy, 4K cinematic quality",
    resolution="1080p",
    duration=5,
)
result = api.wait_for_completion(submission["request_id"])
print(f"Video: {result['outputs'][0]}")

📡 API Endpoints & Reference

1. Seedance 2.5 Spicy Text-to-Video

Endpoint: POST https://api.muapi.ai/api/v1/seedance-2.5-spicy-text-to-video

Field Type Required Default Description
prompt string Yes — Spicy mode favors bolder, higher-contrast, more expressive results.
aspect_ratio enum No 16:9 adaptive, 16:9, 9:16, 1:1, 3:4, 4:3, 21:9
resolution enum No 720p 480p, 720p, 1080p, 4k — price scales with resolution
duration int No 5 Seconds (4-16)
generate_audio boolean No true Whether to generate audio for the video
camera_fixed boolean No false Whether to fix the camera position
high_bitrate boolean No false Higher visual fidelity, larger files
draft boolean No false Generate a cheap 480p draft
draft_request_id string No — Finalize an earlier draft into a full render
curl --location --request POST "https://api.muapi.ai/api/v1/seedance-2.5-spicy-text-to-video" \
  --header "Content-Type: application/json" \
  --header "x-api-key: YOUR_API_KEY" \
  --data-raw '{
      "prompt": "A high-contrast, adrenaline-fueled chase through a rain-soaked neon megacity at night, 4K cinematic quality",
      "resolution": "1080p",
      "duration": 5
  }'

2. Seedance 2.5 Spicy Image-to-Video

Endpoint: POST https://api.muapi.ai/api/v1/seedance-2.5-spicy-image-to-video

Field Type Required Default Description
prompt string Yes — Describes the video motion and style.
image_url string Yes — URL of the input image to animate into video.
last_image string No — Optional last frame image for first-last frame control.
resolution enum No 720p 480p, 720p, 1080p, 4k
duration int No 5 Seconds (4-16)
generate_audio boolean No true Whether to generate audio for the video
camera_fixed boolean No false Whether to fix the camera position
high_bitrate boolean No false Higher visual fidelity, larger files
draft / draft_request_id boolean / string No — Draft → finalize workflow

3. Seedance 2.5 Spicy First & Last Frame

Endpoint: POST https://api.muapi.ai/api/v1/seedance-2.5-spicy-first-last-frame

Generates a smooth video transition between a start and end image, up to 30 seconds.

Field Type Required Default Description
prompt string Yes — Describes the transition and motion.
images_list array[string] Yes — Exactly 2 images: [first_frame, last_frame].
resolution enum No 720p 480p, 720p, 1080p, 4k
duration int No 5 Seconds (4-30)
seed int No -1 Random seed; -1 for random
high_bitrate boolean No false Higher visual fidelity, larger files
draft / draft_request_id boolean / string No — Draft → finalize workflow

4. Seedance 2.5 Spicy Omni Reference

Endpoint: POST https://api.muapi.ai/api/v1/seedance-2.5-spicy-omni-reference

Blends reference images, video clips, and audio into a single guided generation, up to 30 seconds.

Field Type Required Default Description
prompt string Yes — References the images/videos/audio as environment, motion, and mood cues.
images_list array[string] No — Up to 30 reference image URLs.
videos_list array[string] No — Up to 10 reference video URLs.
audios_list array[string] No — Up to 10 reference audio URLs.
resolution enum No 720p 480p, 720p, 1080p, 4k
duration int No 5 Seconds (4-30)
aspect_ratio enum No 16:9 adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 9:21
omni_reference_task_type enum No auto auto, reference, edit, extend — edit/extend require aspect_ratio=adaptive (edit also requires duration=-1)
seed int No -1 Random seed; -1 for random
high_bitrate boolean No false Higher visual fidelity, larger files
draft / draft_request_id boolean / string No — Draft → finalize workflow
curl --location --request POST "https://api.muapi.ai/api/v1/seedance-2.5-spicy-omni-reference" \
  --header "Content-Type: application/json" \
  --header "x-api-key: YOUR_API_KEY" \
  --data-raw '{
      "prompt": "Create a calm cinematic park sequence using the images for environment style and the video clips for camera motion",
      "images_list": ["https://example.com/style1.jpg"],
      "videos_list": ["https://example.com/motion.mp4"]
  }'

5. Seedance 2.5 Spicy Video Edit

Endpoint: POST https://api.muapi.ai/api/v1/seedance-2.5-spicy-video-edit

Edits an input video from a natural-language prompt; the reference video drives subject identity, composition, and motion.

Field Type Required Default Description
prompt string Yes — Automatically prefixed with "Edit the input video."
video_url string Yes — Video to edit; videos longer than 30s are trimmed to 30s.
images_list array[string] No — Up to 30 reference image URLs guiding subject identity/style.
audios_list array[string] No — Up to 10 reference audio URLs.
resolution enum No 720p 480p, 720p, 1080p, 4k
duration int No 5 Seconds (4-30)
generate_audio boolean No true If false, the input video's original audio is preserved.
seed int No -1 Random seed; -1 for random
high_bitrate boolean No false Higher visual fidelity, larger files

6. Seedance 2.5 Spicy Video Extend

Endpoint: POST https://api.muapi.ai/api/v1/seedance-2.5-spicy-video-extend

Extends an input video with a new cinematic continuation generated from its last frame.

Field Type Required Default Description
prompt string Yes — Desired cinematic continuation — action, camera movement, lighting, mood.
video_url string Yes — Generation continues from this video's last frame.
last_image string No — Optional target frame to interpolate toward.
resolution enum No 720p 480p, 720p, 1080p, 4k
duration int No 5 Extension length in seconds (4-30)
generate_audio boolean No true Whether to generate synchronized audio for the new segment
seed int No -1 Random seed; -1 for random
high_bitrate boolean No false Higher visual fidelity, larger files

7. Seedance 2.5 Spicy Motion Control

Endpoint: POST https://api.muapi.ai/api/v1/seedance-2.5-spicy-motion-control

Recasts an existing performance video with a bolder creative treatment while preserving the original motion, choreography, blocking, camera work, and location.

Field Type Required Default Description
video_url string Yes — Reference video whose motion/choreography/camera work is preserved.
images_list array[string] No — Up to 30 character, location, or style reference images.
prompt string No — Optional creative brief; roles are inferred automatically if omitted.
aspect_ratio enum No 16:9 adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 9:21
duration int No 5 Seconds (4-30)
seed int No -1 Random seed; -1 for random
high_bitrate boolean No false Higher visual fidelity, larger files
generate_audio boolean No false Generate audio (music/SFX) for the recast video; off by default.
curl --location --request POST "https://api.muapi.ai/api/v1/seedance-2.5-spicy-motion-control" \
  --header "Content-Type: application/json" \
  --header "x-api-key: YOUR_API_KEY" \
  --data-raw '{
      "video_url": "https://example.com/dance.mp4",
      "images_list": ["https://example.com/performer1.jpg"],
      "prompt": "Recast the dancers with the people in the reference images and use a bold, high-contrast visual treatment"
  }'

💰 Pricing

Endpoint Cost
Seedance 2.5 Spicy Text-to-Video $0.60 / generation (scales with resolution)
Seedance 2.5 Spicy Image-to-Video $0.60 / generation (scales with resolution)
Seedance 2.5 Spicy First & Last Frame $1.87 / generation (scales with resolution)
Seedance 2.5 Spicy Omni Reference $1.87 / generation (scales with resolution)
Seedance 2.5 Spicy Video Edit $1.87 / generation (scales with resolution)
Seedance 2.5 Spicy Video Extend $1.87 / generation (scales with resolution)
Seedance 2.5 Spicy Motion Control $1.65 / generation

Pricing is illustrative and subject to change — check muapi.ai/seedance-2.5-spicy for current rates.


📖 Method Reference

Method Parameters Description
text_to_video prompt, aspect_ratio, duration, resolution, generate_audio, camera_fixed, high_bitrate, draft, draft_request_id Text to Video.
image_to_video prompt, image_url, last_image, duration, resolution, generate_audio, camera_fixed, high_bitrate, draft, draft_request_id Image to Video.
first_last_frame prompt, images_list, resolution, duration, seed, high_bitrate, draft, draft_request_id First & Last Frame transition.
omni_reference prompt, images_list, videos_list, audios_list, resolution, duration, aspect_ratio, omni_reference_task_type, seed, high_bitrate, draft, draft_request_id Omni Reference.
video_edit prompt, video_url, images_list, audios_list, resolution, duration, generate_audio, seed, high_bitrate Video Edit.
video_extend prompt, video_url, last_image, resolution, duration, generate_audio, seed, high_bitrate Video Extend.
motion_control video_url, images_list, prompt, aspect_ratio, duration, seed, high_bitrate, generate_audio Motion Control recast.
upload_file file_path Upload a local file (image, video, or audio) to MuAPI.
get_result request_id Check task status.
wait_for_completion request_id, poll_interval, timeout Blocking helper for generation tasks.

🔗 Official Resources

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.


Keywords: Seedance 2.5 Spicy API, ByteDance Seedance 2.5 Spicy, uncensored AI video generator, relaxed content moderation video API, native 4K video generation, Text-to-Video AI, Image-to-Video API, Omni Reference video generation, Video Edit API, Video Extend API, Motion Control API, Seedance Python SDK, Sora Alternative, MuAPI, Video Generation API, Cinematic AI Video, Python Video API.

Reviews (0)

No results found