alibaba/wan2.7-i2v-spicy-prime
alibaba/wan2.7-i2v-spicy-prime
Turn one image into a 2-15 second HD motion video with 720p/1080p output, optional audio, negative prompts, and prompt expansion.
Examples
Parameters
| Name | Type | Default | Constraints | Description |
|---|---|---|---|---|
| prompt *Prompt | textarea | — | ≤ 5000 chars | Describes the desired subject, action, composition, camera movement, lighting, and style. |
| image *Image | image_upload | — | image/* · 0–1 items | Image URL used as the visual source for the request. |
| audio_urlAudio | audio_upload | — | audio/* · 0–1 items | Audio URL used as an input or timing reference for generation. |
| negative_promptNegative Prompt | textarea | — | ≤ 5000 chars | Describes elements, artifacts, or styles that should be avoided in the output. |
| resolutionResolution | select | 1080p | 720p | 1080p | Selects the output resolution or provider generation mode. Higher settings may take longer to process. |
| durationDuration | slider | 5 | 2 ~ 15 · step 1 | Sets the output video duration in seconds within the supported range. |
| prompt_extendEnable Prompt Expansion | boolean | true | — | Automatically expands short prompts with additional visual detail before generation. |
| seedSeed | number | — | 0 ~ 2147483647 · step 1 | Optional random seed for reproducible results; leave empty to use a random seed. |
| audioInclude Audio | boolean | true | — | Controls whether the generated result includes an audio track. |
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/alibaba/wan2.7-i2v-spicy-prime" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {
"prompt": "Animate the subject with expressive but natural movement, a slow camera push-in, coherent background motion, and cinematic lighting.",
"image": [
"https://assets-public.namifusion.com/marketplace/images/2026-06-12/638e1ee18ac7.jpeg"
],
"resolution": "1080p",
"duration": 5,
"prompt_extend": true,
"audio": true
}
}'
# 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/alibaba/wan2.7-i2v-spicy-prime",
headers=HEADERS,
json={
"input": {
"prompt": "Animate the subject with expressive but natural movement, a slow camera push-in, coherent background motion, and cinematic lighting.",
"image": [
"https://assets-public.namifusion.com/marketplace/images/2026-06-12/638e1ee18ac7.jpeg"
],
"resolution": "1080p",
"duration": 5,
"prompt_extend": True,
"audio": True
}
},
)
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/alibaba/wan2.7-i2v-spicy-prime", {
method: "POST",
headers: { ...HEADERS, "Content-Type": "application/json" },
body: JSON.stringify({
"input": {
"prompt": "Animate the subject with expressive but natural movement, a slow camera push-in, coherent background motion, and cinematic lighting.",
"image": [
"https://assets-public.namifusion.com/marketplace/images/2026-06-12/638e1ee18ac7.jpeg"
],
"resolution": "1080p",
"duration": 5,
"prompt_extend": true,
"audio": true
}
}),
});
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
alibaba/wan2.7-i2v-spicy-prime
Generate high-resolution image-led video with flexible duration and optional audio guidance.
Wan 2.7 I2V Spicy Prime creates a cinematic video from one source image and a detailed motion prompt. It supports native 720p and 1080p output, durations from 2 to 15 seconds, optional audio input, optional generated audio, negative prompts, prompt expansion, and seed control. The broad duration range makes it useful for both short motion tests and finished social or campaign assets.
Key Features
- High-resolution image animation: Produces 720p or 1080p video while using the source image to maintain subject and scene identity.
- Flexible 2-15 second duration: Choose the exact clip length required by the composition.
- Audio-aware workflow: Provide
audio_urlas guidance and control whether the result includes audio withaudio. - Positive and negative prompting: Describe desired motion and explicitly exclude unwanted artifacts or styles.
- Prompt expansion included: Enriches concise prompts without an additional prompt-expansion charge.
- Reproducible iteration: Use
seedto compare prompt or setting changes under similar random conditions.
Technical Specifications
| Item | Details |
|---|---|
| Task | Image-to-video generation |
| Required input | image, prompt |
| Optional guidance | audio_url, negative_prompt |
| Resolution | 720p, 1080p (default) |
| Duration | 2-15 seconds; default 5 seconds |
| Generated audio | Enabled by default; can be disabled |
| Prompt expansion | Supported and enabled by default |
| Output | Generated video URL, with audio when requested |
Sample Prompts
A slow cinematic push-in as the character turns toward the window, realistic cloth and hair motion, soft rain outside, coherent reflections.The camera circles the product while highlights travel across the metal surface; dark premium studio, precise geometry, smooth motion.The illustrated landscape comes alive with drifting fog, moving clouds, swaying grass, and subtle parallax while preserving the original art style.
Pricing
| Resolution | Price per second |
|---|---|
| 720p | 13 credits |
| 1080p | 20 credits |
Prompt expansion is included at no additional charge. Duration multiplies the per-second rate. These values mirror the existing Marketplace pricing configuration; this documentation update does not alter pricing.
Best Use Cases
- High-quality portrait and fashion animation.
- Product advertising with controlled camera movement.
- Music, performance, and rhythm-aware visual clips using audio guidance.
- Concept art, illustration, and cinematic scene animation.
Best Practices
Start with a sharp, well-composed image and describe motion rather than repeating visible objects. Separate subject motion from camera movement, keep the requested action plausible for the clip duration, and use a concise negative prompt for specific artifacts. When audio guidance is supplied, choose material whose rhythm and duration fit the intended scene.
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.