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.
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? |
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": "A cinematic portrait, dramatic rim light, shallow depth of field",
"first_frame": "https://example.com/input.jpg",
"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": "A cinematic portrait, dramatic rim light, shallow depth of field",
"first_frame": "https://example.com/input.jpg",
"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": "A cinematic portrait, dramatic rim light, shallow depth of field",
"first_frame": "https://example.com/input.jpg",
"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 | $0.30 | $0.06 |
| 720p | $0.60 | $0.12 |
| 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 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.
Nami Wan 2.7 I2V Spicy Prime
Create a 2–15 second video from a reference image and prompt, with 720p/1080p output and optional audio guidance.
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.
Kling Omni Video O3 Image-To-Video
Kling Omni Video O3 Image-to-Video transforms static images into dynamic cinematic videos using MVL (Multi-modal Visual Language) technology. Maintains subject consistency while adding natural motion, physics simulation, and seamless scene dynamics. Supports audio generation. Ready-to-use REST API, best performance, no coldstarts, affordable pricing.
Kling Omni Video O1 Image-to-Video
Kling Omni Video O1 Image-to-Video transforms static images into dynamic cinematic videos using MVL (Multi-modal Visual Language) technology. Maintains subject consistency while adding natural motion, physics simulation, and seamless scene dynamics. Ready-to-use REST API, best performance, no coldstarts, affordable pricing.
Kling 3.0 Standard
Kling 3.0 Standard delivers high-quality image-to-video generation with smooth motion, cinematic visuals, accurate prompt adherence, and native audio for ready-to-share clips. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.
Kling V2.6 Image to Video API
Kling 2.6 delivers top-tier image-to-video generation with smooth motion, cinematic visuals, accurate prompt adherence, and native audio for ready-to-share clips. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.