Seedance 2.0 Mini Image to Video
doubao/seedance-2.0-mini/image-to-video
Seedance 2.0 Mini 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 across scenes, 480P / 720P / 1080P / 4K output, 4-15s duration, and flexible aspect ratios. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Examples
Parameters
| Name | Type | Default | Constraints | Description |
|---|---|---|---|---|
| prompt *Prompt | textarea | — | ≤ 5000 chars | Describe the scene, action, camera movement, and mood for the video. |
| first_frame *Image | image_upload | — | image/* · 0–1 items | Start image URL to guide the video generation. |
| last_frameLast Image | image_upload | — | image/* · 0–1 items | Last frame image URL for video continuation. |
| ratioAspect Ratio | select | — | 16:9 | 9:16 | 4:3 | 3:4 | 1:1 | 21:9 | The aspect ratio of the generated video. If not specified, adapts to the input image. |
| resolutionResolution | select | 720p | 480p | 720p | The output video resolution. |
| durationDuration | slider | 5 | 4 ~ 15 · step 1 | The duration of the generated video in seconds (4-15s). |
| generate_audioGenerate Audio | boolean | true | — | Whether to generate native audio synchronized with the output video. Defaults to true. |
| enable_web_searchEnable Web Search | boolean | false | — | Enable web search for real-time information. |
| return_last_framereturn the last frame | boolean | — | — | Should the last frame of the generated video be returned? |
Output fields
| Field | Type | Description |
|---|---|---|
| videos | array<string> | Generated video URL(s). |
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/image-to-video" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {
"prompt": "Create a cinematic slow push-in with natural subject motion, gentle environmental movement, and stable lighting.",
"first_frame": [
"https://assets-public.namifusion.com/marketplace/images/2026-06-12/638e1ee18ac7.jpeg"
],
"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/image-to-video",
headers=HEADERS,
json={
"input": {
"prompt": "Create a cinematic slow push-in with natural subject motion, gentle environmental movement, and stable lighting.",
"first_frame": [
"https://assets-public.namifusion.com/marketplace/images/2026-06-12/638e1ee18ac7.jpeg"
],
"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/image-to-video", {
method: "POST",
headers: { ...HEADERS, "Content-Type": "application/json" },
body: JSON.stringify({
"input": {
"prompt": "Create a cinematic slow push-in with natural subject motion, gentle environmental movement, and stable lighting.",
"first_frame": [
"https://assets-public.namifusion.com/marketplace/images/2026-06-12/638e1ee18ac7.jpeg"
],
"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
Seedance 2.0 Mini Image to Video API
A faster, lower-cost image-to-video model for cinematic multi-shot storytelling with native audio support.
Seedance 2.0 Mini Image to Video is ByteDance’s efficient image-to-video model for turning a reference image and optional prompt into short narrative video sequences. It is designed to balance speed, affordability, and visual quality, with flexible aspect ratios, multi-resolution output up to 4K, character consistency across scenes, and no cold start performance for production-ready generation.
🚀 Key Features
- Image-to-video generation: Transform a single reference image into a dynamic video sequence guided by a text prompt.
- Prompt-guided motion and camera control: Describe scene composition, subject action, camera movement, and mood for more controllable outputs.
- Optional last-frame guidance: Use
last_imageto steer the ending frame or continuation direction of the generated video. - Native audio generation: Generate synchronized audio together with the output video to reduce post-production effort.
- Flexible aspect ratios and resolution options: Support for 16:9, 9:16, 4:3, 3:4, 1:1, and 21:9, with output from 480p to 4k.
- Fast, affordable, and no cold start: Optimized for responsive inference and cost-efficient generation in iterative or large-scale workflows.
🛠️ Technical Specifications
| Item | Details |
|---|---|
| Model architecture | Image-to-video model for cinematic multi-shot video generation |
| Input format | Image URL + prompt, with optional last_image for ending-frame guidance |
| Output format | Video, with optional native audio |
| Resolution | 480p, 720p, 1080p, 4k |
| Default resolution | 720p |
| Duration | 4–15 seconds |
| Default duration | 5 seconds |
| Aspect Ratio | 16:9, 9:16, 4:3, 3:4, 1:1, 21:9; adapts to the input image if unspecified |
| Audio | Supported; synchronized native audio enabled by default |
| Last-frame control | Supported via last_image |
| Real-time information enhancement | Optional enable_web_search support |
| Latency | Optimized for fast inference with no cold start |
| Best suited for | Cinematic clips, social content, concept visualization, creative prototyping |
Sample Prompts
- A cinematic shot of a character slowly walking through a neon-lit street at night, soft rain falling, reflections on the wet pavement, gentle handheld camera movement, atmospheric lighting, calm but dramatic mood.
- A futuristic sports car racing along a coastal highway at sunrise, low-angle tracking shot, sunlight cutting through light fog, energetic motion, premium commercial look.
- A lone traveler standing on a mountain peak above the clouds, slow camera push-in, wind moving the clothing, cool morning light, epic yet peaceful atmosphere.
💰 Pricing
| Service Type | Resolution | Price |
|---|---|---|
| Video Gen (T2V/I2V) | all | $3.5 / 1M Tokens |
| Video Gen (V2V) | all | $2.1 / 1M Tokens |
Estimate Costs by Duration
| Resolution | Price per 5 seconds | Price per second |
|---|---|---|
| 480p | $0.168 | $0.0336 |
| 720p | $0.378 | $0.0756 |
| 1080p | $1.50 | $0.30 |
| 4k | $3.00 | $0.60 |
💡 Best Use Cases
- Social media content production: Create vertical, square, landscape, or ultrawide short-form videos for modern content platforms.
- E-commerce and brand marketing: Turn product visuals or campaign key art into motion-rich promotional clips.
- Previsualization and storyboard testing: Explore scene direction, camera movement, and mood before full production.
- Creative concept development: Prototype character-driven or world-building sequences from a single visual reference.
🔗 Related Models
- Bytedance Seedance 2.0 Image To Video Turbo: A related variant better suited for workflows prioritizing higher throughput and faster generation.
- Bytedance Seedance 2.0 Mini Image To Video Spicy: Another model in the same family for exploring alternative generation styles or output tendencies.
Related models
xAI Grok Imagine Video v1.5 Image to Video
Animate one input image with a text prompt into a 1-15 second video at 480p or 720p.
Vidu Q4 Preview Image to Video
Generate a 3–16 second video from a prompt and one image, with optional audio and prompt expansion. Supports 540p, 720p, 1080p, 2k and 4k.
vidu/q3/image-to-video-spicy
Vidu Q3 Image-to-Video Spicy generates unlimited high-quality videos from images with smooth animations and diverse motion, optimized for scalable content generation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Vidu Q3 Image To Video
Vidu Q3 Image-to-Video turns text prompts into high-quality videos with exceptional visual fidelity and diverse motion. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

MiniMax H3 Spicy Image to Video
Animate a first-frame image with optional prompt and last-frame guidance. Supports 480p, 540p, 768p and 1080p video, with durations from 3 to 15 seconds.
MiniMax H3 Image to Video
MiniMax H3 Image to Video animates a first-frame image into a coherent 2K video, with natural-language motion instructions and optional last-frame control for consistent motion, scene continuity, and cinematic video generation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
ltx-2.5/image-to-video
LTX 2.5 Image-to-Video animates a first-frame image into high-fidelity synchronized audio-video content, with optional last-frame guidance and 720P / 1080P / 2K / 4K output for cinematic videos, social content, ads, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
ai/ltx-2.3-spicy/image-to-video-lora
LTX 2.3 Spicy LoRA Image to Video API turns a reference image and prompt into expressive AI videos using selectable LoRA presets, optional LoRA strength overrides, duration, and resolution controls. Run fast REST inference on MaaS with no cold starts and affordable pricing.