Seedance 2.0 Mini Reference to Video

doubao/seedance-2.0-mini/reference-to-video

Seedance 2.0 Mini Reference-to-Video is a high-speed, cost-effective video generation model developed by ByteDance, engineered specifically for creating multi-shot videos with a cinematic feel. By seamlessly combining reference images with text prompts, it generates highly narrative video segments. The model features advanced AI camera control and ensures robust character consistency across different scenes. It supports multiple output resolutions from 480P up to 4K, durations ranging from 4 to 15 seconds, and flexible aspect ratios. Complete with an out-of-the-box REST inference API, it delivers exceptional performance with zero cold starts, offering an affordable yet premium solution for professional video creation.

Examples

Seedance 2.0 Mini Reference to Video example 1

Parameters

NameTypeDefaultConstraintsDescription
prompt *Prompttextarea≤ 5000 charsDescribe the scene, action, camera movement, and mood for the video.
imagesReference Imagesimage_uploadimage/* · 0–9 itemsReference image URLs to guide visual style, characters, or scene composition.
videosReference Videosvideo_upload_groupvideo/* · 0–3 itemsReference video URLs (total length must not exceed 15 seconds).
audiosReference Audiosaudio_upload_groupaudio/* · 0–3 itemsReference audio URLs (total length must not exceed 15 seconds).
ratioAspect Ratioselect16:916:9 | 9:16 | 4:3 | 3:4 | 1:1 | 21:9The aspect ratio of the generated video.
resolutionResolutionselect720p480p | 720pThe output video resolution.
durationDurationslider54 ~ 15 · step 1The duration of the generated video in seconds (4-15s).
generate_audioGenerate AudiobooleantrueWhether to generate native audio synchronized with the output video. Defaults to true.
enable_web_searchEnable Web SearchbooleanfalseEnable web search for real-time information.
return_last_framereturn the last frame booleanShould the last frame of the generated video be returned?

API

Call this model through one unified REST API. Get a key on the API Keys page.

cURL
# 1) Submit — returns { "task_uuid": "..." }
curl -X POST "https://www.namifusion.com/api/v1/marketplace/run/doubao/seedance-2.0-mini/reference-to-video" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "input": {
    "prompt": "A cinematic portrait, dramatic rim light, shallow depth of field",
    "ratio": "16:9",
    "resolution": "720p",
    "duration": 5,
    "generate_audio": true,
    "enable_web_search": false
  }
}'

# 2) Poll until status is "completed", then read the output URLs
curl "https://www.namifusion.com/api/v1/marketplace/run/tasks/TASK_UUID" \
  -H "Authorization: Bearer YOUR_API_KEY"
Python
import time, requests

API_KEY = "YOUR_API_KEY"
HEADERS = {"Authorization": f"Bearer {API_KEY}"}

# 1) Submit
resp = requests.post(
    "https://www.namifusion.com/api/v1/marketplace/run/doubao/seedance-2.0-mini/reference-to-video",
    headers=HEADERS,
    json={
        "input": {
            "prompt": "A cinematic portrait, dramatic rim light, shallow depth of field",
            "ratio": "16:9",
            "resolution": "720p",
            "duration": 5,
            "generate_audio": True,
            "enable_web_search": False
        }
    },
)
resp.raise_for_status()  # 401/402/429/5xx stop here instead of polling a bad task
task = resp.json()

# 2) Poll until a terminal state (completed / failed / cancelled).
#    This model is allowed up to 300s server-side.
deadline = time.time() + 360
while task.get("status") not in ("completed", "failed", "cancelled"):
    if time.time() > deadline:
        raise TimeoutError(f"still {task.get('status')} — keep the task_uuid and poll later")
    time.sleep(3)
    poll = requests.get(f"https://www.namifusion.com/api/v1/marketplace/run/tasks/{task['task_uuid']}", headers=HEADERS)
    poll.raise_for_status()
    task = poll.json()

print(task["status"], task.get("output"))
JavaScript
const API_KEY = "YOUR_API_KEY";
const HEADERS = { Authorization: `Bearer ${API_KEY}` };

// 1) Submit
const resp = await fetch("https://www.namifusion.com/api/v1/marketplace/run/doubao/seedance-2.0-mini/reference-to-video", {
  method: "POST",
  headers: { ...HEADERS, "Content-Type": "application/json" },
  body: JSON.stringify({
    "input": {
      "prompt": "A cinematic portrait, dramatic rim light, shallow depth of field",
      "ratio": "16:9",
      "resolution": "720p",
      "duration": 5,
      "generate_audio": true,
      "enable_web_search": false
    }
  }),
});
if (!resp.ok) throw new Error(`submit failed: ${resp.status} ${await resp.text()}`);
let task = await resp.json();

// 2) Poll until a terminal state (completed / failed / cancelled).
//    This model is allowed up to 300s server-side.
const deadline = Date.now() + 360 * 1000;
while (!["completed", "failed", "cancelled"].includes(task.status)) {
  if (Date.now() > deadline) throw new Error(`still ${task.status} — keep the task_uuid and poll later`);
  await new Promise((r) => setTimeout(r, 3000));
  const poll = await fetch(`https://www.namifusion.com/api/v1/marketplace/run/tasks/${task.task_uuid}`, { headers: HEADERS });
  if (!poll.ok) throw new Error(`poll failed: ${poll.status}`);
  task = await poll.json();
}

console.log(task.status, task.output);

Documentation

Doubao-Seedance 2.0 Mini (Reference-to-Video)

The "Film Studio in a Model": Precision Control with Flexible Multi-Modal Reference.

Seedance 2.0 Mini (Reference-to-Video) is ByteDance's highly cost-effective next-generation video generation model. Featuring a revolutionary Multi-modal Reference System, it provides ultimate flexibility: users can either provide an input reference video to perform video-to-video (V2V) styling, or skip the video input entirely to generate video from text, images, and audio, keeping pixel-perfect control over characters, motion, and rhythm.

🚀 Key Features

  • Flexible Input Workflows: Native support for both Video-to-Video (with input video) and text/image-to-video (no input video) modes under a single model pipeline.
  • Multi-modal Fusion: Supports simultaneous blending of 9 images + 3 videos + 3 audio clips (up to 12 total) to ensure flawless character and scene consistency.
  • Audio-Visual Synchronicity: Native support for lip-sync and rhythm matching, automatically aligning visual motion with background music or speech.
  • Exceptional Physical Logic: Advanced simulation of fluid dynamics, gravity, and complex movements with optimized generation speed for rapid iteration.
  • Pro Camera Control: Direct language-based control over cinematic camera movements (pan, tilt, zoom) and lighting transitions.

🛠️ Technical Specifications

ParameterDetails
Model IDdoubao/seedance-2.0-mini/reference-to-video
Model ArchitectureDiffusion-based Transformer (DiT) / Multi-modal
Max Resolution720P (Cost & speed optimized)
Video Duration4 - 15 Seconds
Aspect Ratios16:9, 9:16, 4:3, 3:4, 21:9, 1:1
Input ModalityReference Video (Optional), Text, Image (up to 9), Audio (up to 3)
Generation Speed~20-60 seconds per clip (Mini-optimized)

Sample Prompts

  • Scenario A (With Input Video): "Keep the motion and camera movement of @ReferenceVideo1, but change the art style to cyberpunk anime with neon lighting."
  • Scenario B (No Input Video): "Use @Image1 as the main character, generate a motion of him walking down a rainy city street at night, and match the tempo of @Audio1."

💰 Pricing (Volcengine API)

Service TypeResolutionInput Video StatusPrice
Video Gen (Reference)480pWith Input Video$2.100 / 1M Tokens
Video Gen (Reference)480pNo Input Video$3.500 / 1M Tokens
Video Gen (Reference)720pWith Input Video$2.100 / 1M Tokens
Video Gen (Reference)720pNo Input Video$3.500 / 1M Tokens

💡 Best Use Cases

  • Video-to-Video Style Transfer: Instantly converting live-action footage into anime, 3D claymation, or cinematic sci-fi styles.
  • High-Volume Rapid Mockups: Using text and image references to test multiple creative variations cheaply and twice as fast as standard tiers.
  • E-commerce Content & MVs: Rapidly creating product promos and syncing visual transitions or lip-movements to a song or voice clip without high hardware overhead.

Related models

xAI Grok Imagine Video v1.5 Reference to Video
Reference to VideoX Ai

xAI Grok Imagine Video v1.5 Reference to Video

Generate a 1-15 second video from a prompt and 1-7 reference images at 480p or 720p.

from $0.840 / per run
MiniMax H3 Reference to Video
Reference to VideoMinimax

MiniMax H3 Reference to Video

MiniMax H3 Reference to Video generates coherent 2K videos from natural-language prompts and multimodal references, including images, videos, and audio, guiding subject consistency, motion, timing, visual style, and scene continuity. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

from $0.650 / per run
Gemini Omni Flash Reference to Video API
Reference to VideoGoogle

Gemini Omni Flash Reference to Video API

Gemini Omni Flash Reference to Video creates short AI videos with synchronized audio from one or more reference images and a text prompt, preserving visual identity and following the provided references for guided multimodal video generation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

from $1.28 / per run
Seedance 2.5 Reference to Video
Reference to VideoDoubao

Seedance 2.5 Reference to Video

The "Reference-to-Video" feature of Seedance 2.5 is the ultimate solution for visual stylistic unity. It precisely extracts artistic styles, lighting tones, or compositional intents from reference materials and seamlessly integrates them into newly generated videos, ensuring a highly consistent visual language for your creative series.

from $0.700 / per run
Seedance 2.0 Fast reference-to-video
Reference to VideoDoubao

Seedance 2.0 Fast reference-to-video

Seedance 2.0 Fast (Video-Edit) edits an input video from a natural-language prompt at a faster, cheaper tier. Built on ByteDance Seed's unified multimodal architecture, it preserves subject identity, composition, and motion while rewriting lighting, style, weather, environment, or specific elements as instructed. Ready-to-use REST API, best performance, no coldstarts, affordable pricing.

from $0.720 / per run