Bytedance Seedance 2.0 Mini Image To Video Spicy API Documentation

Bytedance Seedance 2.0 Mini Image To Video Spicy API Documentation

Playground

Seedance 2.0 Mini Spicy Image to Video is ByteDance’s faster, lower-cost image-to-video model for cinematic multi-shot videos. It turns reference images and optional text prompts into narrative sequences with AI camera control, consistent characters, 480P / 720P / 1080P / 4K output, 4-15s duration, and flexible aspect ratios. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

ByteDance Seedance 2.0 Mini Image-to-Video Spicy generates videos from a start image, with optional prompt guidance, last-frame guidance, native audio generation, and seed control. Upload an image, choose the output resolution and duration, and generate a video in 480p, 720p, 1080p, or 4k.

• Need the standard image-to-video version instead? Try ByteDance Seedance 2.0 Mini Image-to-Video.
• Need to generate from text instead? Try ByteDance Seedance 2.0 Mini Text-to-Video.

Why Choose This?

• Image-to-video generation
  Turn a start image into a generated video.

• Optional prompt guidance
  Describe the scene, action, camera movement, and mood for the video.

• Last-frame guidance
  Use last_image to guide the final frame or continuation direction.

• Native audio generation
  Generate synchronized audio together with the output video using generate_audio.

• Flexible aspect ratios
  Choose from 16:9, 9:16, 4:3, 3:4, 1:1, and 21:9, or let the output adapt to the input image.

• Seed control
  Use a fixed seed for more reproducible outputs, or -1 for a random seed.

Parameters

How to Use

1. Upload the start image — Provide the image that should guide the video generation.
2. Write a prompt optional — Describe the scene, motion, camera behavior, lighting, and mood.
3. Add a last image optional — Use last_image when you want to guide the final frame.
4. Choose aspect ratio optional — Select a supported aspect ratio, or leave it empty to adapt to the input image.
5. Choose resolution — Select 480p, 720p, 1080p, or 4k.
6. Set duration — Choose a duration between 4 and 15 seconds.
7. Configure audio optional — Keep generate_audio enabled for synchronized native audio, or disable it if audio is not needed.
8. Set seed optional — Use a fixed seed for reproducible outputs, or -1 for random generation.
9. Submit — Generate the final video.

Example Prompt

A cinematic shot of the character slowly walking through a neon-lit street at night, soft rain falling, reflections on the wet pavement, gentle camera movement, atmospheric lighting, calm but dramatic mood.

Writing Effective Prompts

The input image sets the first frame — your prompt directs what happens from there. The clearer the motion and camera direction, the better the result.

1. Start from the frame

Describe the action that begins from your image: what the subject does, where it goes, how the camera moves. Don’t re-describe what’s already visible in the image — build on it.

The woman in the photo turns from the window and walks toward the camera; slow push-in, warm interior light.

2. Shot-by-shot timeline

For longer clips, break the motion into timed segments (1-second granularity), continuous, no gaps.

> 0-2s: She turns from the window, a faint smile forming. Camera holds. > 2-5s: She walks toward the lens and stops mid-frame; slow push-in, shallow focus. > 5-8s: She glances off-screen as light shifts from warm to cool. Handheld drift.

3. Consistency notes

Lock the look for the whole clip: camera style, lighting, palette, atmosphere, audio.

Camera language

Write these directly; the model understands them:

• Shot size — extreme wide, wide, medium, medium close-up, close-up
• Movement — push in, pull out, pan, track, follow, orbit, tilt up, handheld shake
• Angle — low angle, overhead, eye-level, first-person
• Techniques — one-shot / long take, dolly zoom, bullet time, speed ramp

For a niche term, add a plain-language gloss: “rack focus: the sharp foreground softens as the background comes into focus.”

Referencing uploaded assets

When you attach images, videos, or audio, bind each one explicitly in the prompt by its upload order — @image1, @video1, @audio1 — and say what it’s for. Don’t rely on labels drawn inside the image itself.

• “The knight in @image1 walks through the castle in @image2.”
• “Refer to @video1 for the camera movement only; keep its shot order.”
• “@image1 and @image2 are Character 1, voiced by @audio1.”

When a reference is already accurate, just point to it — no need to re-describe it in detail.

Negative control

Positive descriptions work best, but you can suppress subtitles and audio:

• “No subtitles.”
• “No BGM — ambient and action sounds only.”
• “No audio.”

Weak vs. strong

Pricing

Per 5 Seconds

Per Second

Example Costs

Best Use Cases

• Image-to-video animation — Generate motion from a single start image.
• Start-and-end-frame guidance — Use image and last_image to guide the beginning and ending of the video.
• Cinematic short clips — Create short videos with motion, atmosphere, and synchronized audio.
• Social media content — Generate vertical, square, landscape, or ultra-wide video formats.
• Creative prototyping — Test scene ideas, motion concepts, and visual directions from a reference image.

Pro Tips

• Use a clear start image with the main subject visible.
• Use last_image when the final frame or ending direction matters.
• Keep prompts focused on visible motion, camera behavior, lighting, and mood.
• Use 480p for quick testing, 720p for standard output, 1080p for higher-resolution results, and 4k for maximum-resolution output.
• Keep generate_audio enabled when you want the video to include synchronized native audio.
• Use a fixed seed when you want more reproducible outputs.

Related Models

• ByteDance Seedance 2.0 Mini Image-to-Video — Generate video from a start image and prompt.
• ByteDance Seedance 2.0 Mini Text-to-Video — Generate video directly from text prompts.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
  "aspect_ratio": "16:9",
  "resolution": "720p",
  "duration": 5,
  "generate_audio": true
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/bytedance/seedance-2.0-mini/image-to-video-spicy" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters