seedance-2.5/image-to-video-spicy
doubao/seedance-2.5/image-to-video-spicy
Seedance 2.5 Spicy Image to Video is a fast AI image-to-video generation model that creates high-quality cinematic clips from images, optimized for scalable content generation with smooth animations and stable aesthetics. Ready-to-use REST inference API for animating images, social media clips, product videos, advertising creatives, visual storytelling, and professional image-to-video workflows with simple integration, no coldstarts, and affordable pricing.
Examples
Parameters
| Name | Type | Default | Constraints | Description |
|---|---|---|---|---|
| first_frame *Image | image_upload | — | image/* · 0–1 items | Start image URL to guide the video generation. |
| promptPrompt | textarea | — | ≤ 5000 chars | Describe the scene, action, camera movement, and mood for the video. |
| last_frameLast Frame | image_upload | — | image/* · 0–1 items | Last frame image URL for video continuation. |
| resolutionResolution | select | 720p | 480p | 720p | 1080p | 4k | The output video resolution. |
| durationDuration | slider | 5 | 4 ~ 30 · step 1 | The duration of the generated video in seconds (4-30s). |
| generate_audioGenerate Audio | boolean | true | — | Whether to generate native audio synchronized with the output video. Defaults to true. |
| seedSeed | number | — | — | The random seed to use for the generation. -1 means a random seed will be used. |
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-2.5/image-to-video-spicy" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {
"first_frame": [
"https://d1s3annbwribom.cloudfront.net/marketplace/examples/2026/09/12/3b144f48e29e.jpeg"
],
"prompt": "A cinematic luxury product shot of the perfume bottle slowly rotating on a reflective surface as soft mist drifts around it. The camera performs a gentle push-in with subtle parallax, highlights glint across the glass, and the mood feels elegant, premium, and atmospheric.",
"last_frame": [
"https://d1s3annbwribom.cloudfront.net/marketplace/examples/2026/09/12/b97d8e67d2ce.jpeg"
],
"resolution": "1080p",
"duration": 6,
"generate_audio": true,
"seed": -1
}
}'
# 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-2.5/image-to-video-spicy",
headers=HEADERS,
json={
"input": {
"first_frame": [
"https://d1s3annbwribom.cloudfront.net/marketplace/examples/2026/09/12/3b144f48e29e.jpeg"
],
"prompt": "A cinematic luxury product shot of the perfume bottle slowly rotating on a reflective surface as soft mist drifts around it. The camera performs a gentle push-in with subtle parallax, highlights glint across the glass, and the mood feels elegant, premium, and atmospheric.",
"last_frame": [
"https://d1s3annbwribom.cloudfront.net/marketplace/examples/2026/09/12/b97d8e67d2ce.jpeg"
],
"resolution": "1080p",
"duration": 6,
"generate_audio": True,
"seed": -1
}
},
)
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-2.5/image-to-video-spicy", {
method: "POST",
headers: { ...HEADERS, "Content-Type": "application/json" },
body: JSON.stringify({
"input": {
"first_frame": [
"https://d1s3annbwribom.cloudfront.net/marketplace/examples/2026/09/12/3b144f48e29e.jpeg"
],
"prompt": "A cinematic luxury product shot of the perfume bottle slowly rotating on a reflective surface as soft mist drifts around it. The camera performs a gentle push-in with subtle parallax, highlights glint across the glass, and the mood feels elegant, premium, and atmospheric.",
"last_frame": [
"https://d1s3annbwribom.cloudfront.net/marketplace/examples/2026/09/12/b97d8e67d2ce.jpeg"
],
"resolution": "1080p",
"duration": 6,
"generate_audio": true,
"seed": -1
}
}),
});
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-2.5/image-to-video-spicy
Fast, expressive image-to-video generation with cinematic motion and stable aesthetics.
doubao/seedance-2.5/image-to-video-spicy is a high-performance image-to-video model designed to turn still images into polished cinematic clips. It combines smooth motion, strong image fidelity, optional native audio, and no-cold-start inference, making it well suited for scalable creative production and professional content workflows.
🚀 Key Features
- Cinematic motion generation: Transforms a single image into a dynamic clip with bold, expressive movement and strong visual impact.
- Image-faithful results: Preserves subject identity, composition, lighting, and overall style while introducing motion.
- Stable temporal coherence: Produces smooth animation with consistent aesthetics across frames, suitable for production use.
- Optional last-frame guidance: Use
last_frameto steer the ending composition or continuation direction of the clip. - Native synchronized audio: Can generate audio together with the video for more complete short-form outputs.
- Flexible quality-cost scaling: Supports
480p,720p,1080p, and4k, with affordable pricing and no cold start.
🛠️ Technical Specifications
| Item | Details |
|---|---|
| Model architecture | Image-to-Video generation model |
| Input format | Image URL, Prompt, optional last-frame image URL |
| Output format | Video, optionally with native synchronized audio |
| Image | first_frame(required), used as the starting frame reference |
| Prompt | prompt(optional), describes motion, scene progression, camera behavior, and mood |
| Last-frame guidance | last_frame(optional), guides the final frame or ending composition |
| Resolution | 480p, 720p, 1080p, 4k(default: 720p) |
| Duration | 4–30 seconds(default: 5) |
| Audio | generate_audio(default: true) |
| Seed | seed, supports reproducible generation; -1 for random |
| Aspect Ratio | Automatically follows the input image |
| Latency | Optimized for fast inference with no cold start |
| Typical workflows | Social clips, product videos, ad creatives, visual storytelling, professional image-to-video pipelines |
Sample Prompts
- The woman in the image turns from the window and walks slowly toward the camera; slow push-in, warm interior light, cinematic mood.
- The parked car in the image pulls out and drives down the wet street. 0–3s: headlights switch on and the car eases forward, reflections rippling on the asphalt. 3–6s: it accelerates past the camera, which pans to follow. Low angle, neon reflections, light rain, no music, only engine and ambient rain sounds.
- 0–2s: the character looks up into the distance, hair moving in the wind. 2–5s: the camera orbits halfway around the subject as the lighting shifts from warm to cool. Shallow depth of field, restrained handheld feel.
💰 Pricing
| Resolution | Per 5s | Per second |
|---|---|---|
| 480p | $0.90 | $0.18 |
| 720p | $1.80 | $0.36 |
| 1080p | $4.50 | $0.90 |
| 4k | $9.00 | $1.80 |
Example Costs
| Resolution | 5s | 10s | 15s | 30s |
|---|---|---|---|---|
| 480p | $0.90 | $1.80 | $2.70 | $5.40 |
| 720p | $1.80 | $3.60 | $5.40 | $10.80 |
| 1080p | $4.50 | $9.00 | $13.50 | $27.00 |
| 4k | $9.00 | $18.00 | $27.00 | $54.00 |
💡 Best Use Cases
- Social media content: Animate still images into short-form clips for vertical, square, or landscape publishing.
- Advertising and e-commerce: Turn product shots or campaign visuals into motion creatives for testing and promotion.
- Character and illustration animation: Bring portraits, concept art, and illustrated subjects to life with controlled motion.
- Previsualization and motion prototyping: Explore camera movement, pacing, and atmosphere before full production.
🔗 Related Models
- Seedance 2.5 Text-to-Video: Generates video directly from text-only Prompt input.
- Seedance 2.5 Video Edit: Edits existing video content with Prompt-based control.
- Seedance 2.5 Video Extend: Extends an existing video with a new generated segment.
- Seedance 2.0 Image-to-Video: Previous-generation image-to-video model for comparison or legacy workflows.
Nami API usage
Send JSON { "input": { ... } } with an X-API-Key header. Each image parameter is an array containing one URL. Defaults below apply when a parameter is omitted; the playground and API examples use the example values shown below.
POST /api/v1/marketplace/run/doubao/seedance-2.5/image-to-video-spicy
| Parameter | Type | Required | Default | Constraints |
|---|---|---|---|---|
first_frame | string[] | yes | — | 1 URL |
prompt | string | no | — | max 5000 characters |
last_frame | string[] | no | — | 0–1 URL |
resolution | string | no | "720p" | 480p, 720p, 1080p, 4k |
duration | integer | no | 5 | 4–30; step 1 |
generate_audio | boolean | no | true | — |
seed | integer | no | — | — |
{
"input": {
"first_frame": [
"https://d1s3annbwribom.cloudfront.net/marketplace/examples/2026/09/12/3b144f48e29e.jpeg"
],
"prompt": "A cinematic luxury product shot of the perfume bottle slowly rotating on a reflective surface as soft mist drifts around it. The camera performs a gentle push-in with subtle parallax, highlights glint across the glass, and the mood feels elegant, premium, and atmospheric.",
"last_frame": [
"https://d1s3annbwribom.cloudfront.net/marketplace/examples/2026/09/12/b97d8e67d2ce.jpeg"
],
"resolution": "1080p",
"duration": 6,
"generate_audio": true,
"seed": -1
}
}
The create response contains task_uuid and task status. Poll using the same API key:
GET /api/v1/marketplace/run/tasks/{task_uuid}
On completion, read generated video URLs from output.videos.
{
"status": "completed",
"output": {
"videos": [
"https://cdn.example.com/output/video.mp4"
]
}
}
This is a response excerpt; see the API tab for the full task structure.
List price is calculated from the selected resolution and duration; 1 USD = 100 credits.
| Resolution | USD / second | Credits / second | USD / 5 seconds |
|---|---|---|---|
| 480p | $0.18 | 18 | $0.90 |
| 720p | $0.36 | 36 | $1.80 |
| 1080p | $0.90 | 90 | $4.50 |
| 4k | $1.80 | 180 | $9.00 |
Enabling or disabling audio does not change the list price.
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-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.
ai/ltx-2.3-spicy/image-to-video
LTX 2.3 Spicy Image-to-Video API generates expressive AI videos from a reference image and prompt. Choose style presets, duration, and resolution with fast REST inference, no cold starts, and affordable pricing on MaaS.