alibaba/wan-2.6/image-to-video-spicy
alibaba/wan-2.6/image-to-video-spicy
alibaba/wan-2.6/image-to-video-spicy. Przeglądaj API modeli obrazu, wideo i zamiany twarzy. Wypróbuj model, a następnie zintegruj go przez wspólne REST API.
Powiązane modele
Pełne parametry, schemat wyjścia i aktualne ceny
| Rynek API modeli AI | Jedna platforma do wszystkiego | Najpopularniejszy | Regulamin | Przeglądaj API modeli obrazu, wideo i zamiany twarzy. Wypróbuj model, a następnie zintegruj go przez wspólne REST API. |
|---|---|---|---|---|
| image_url *Image | image_upload | — | 1–1 items | |
| audio_urlAudioc URL | audio_upload | — | — | |
| promptPrompt | textarea | — | ≤ 1500 chars | |
| negative_promptNegative Prompt | textarea | — | ≤ 1500 chars | |
| resolutionResolution | select | 720p | 720p | 1080p | |
| durationDuration | select | 5 | 5 | 10 | 15 | |
| shot_typeShot Type | select | single | single | multi | |
| prompt_extendEnable Prompt Expansion | boolean | true | — | |
| seedSeed | number | — | ≥ 0 |
Pełne parametry, schemat wyjścia i aktualne ceny
| Dowiedz się więcej | Jedna platforma do wszystkiego | Przeglądaj API modeli obrazu, wideo i zamiany twarzy. Wypróbuj model, a następnie zintegruj go przez wspólne REST API. |
|---|---|---|
| videos | array<string> |
API
Przeglądaj API modeli obrazu, wideo i zamiany twarzy. Wypróbuj model, a następnie zintegruj go przez wspólne REST API.
cURL
# 1) Submit — returns { "task_uuid": "..." }
curl -X POST "https://www.namifusion.com/api/v1/marketplace/run/alibaba/wan-2.6/image-to-video-spicy" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {
"image_url": [
"https://assets-public.namifusion.com/uploads/images/2026-03-05/559f2f35a8de.png"
],
"prompt": "Create a dynamic video showcasing the transition from day to night in a busy city.",
"negative_prompt": "Avoid using any blurred or low-resolution scenes.",
"resolution": "1080P",
"duration": 10,
"shot_type": "multi",
"prompt_extend": 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/alibaba/wan-2.6/image-to-video-spicy",
headers=HEADERS,
json={
"input": {
"image_url": [
"https://assets-public.namifusion.com/uploads/images/2026-03-05/559f2f35a8de.png"
],
"prompt": "Create a dynamic video showcasing the transition from day to night in a busy city.",
"negative_prompt": "Avoid using any blurred or low-resolution scenes.",
"resolution": "1080P",
"duration": 10,
"shot_type": "multi",
"prompt_extend": 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/alibaba/wan-2.6/image-to-video-spicy", {
method: "POST",
headers: { ...HEADERS, "Content-Type": "application/json" },
body: JSON.stringify({
"input": {
"image_url": [
"https://assets-public.namifusion.com/uploads/images/2026-03-05/559f2f35a8de.png"
],
"prompt": "Create a dynamic video showcasing the transition from day to night in a busy city.",
"negative_prompt": "Avoid using any blurred or low-resolution scenes.",
"resolution": "1080P",
"duration": 10,
"shot_type": "multi",
"prompt_extend": 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);Dokumentacja API
alibaba/wan-2.6/image-to-video-spicy
Turn still images into expressive, high-quality videos with smooth cinematic motion.
alibaba/wan-2.6/image-to-video-spicy is an image-to-video model designed for scalable content production. It transforms a single image into dynamic video clips with natural transitions, vivid motion, and strong visual impact, while offering no cold starts and support for both 720p and native 1080p output.
🚀 Key Features
- High-quality image-to-video generation: Animate still images into polished video clips with smooth, temporally coherent motion.
- Native 720p and 1080p output: Choose the resolution that best fits your quality and budget requirements.
- Flexible clip durations: Generate 5s, 10s, or 15s videos for short-form content, ads, and storytelling.
- Single-shot or multi-shot modes: Use
shot_typeto create either stable single-shot animations or more dynamic multi-shot sequences. - Prompt expansion support: Enable automatic prompt optimization to enrich descriptions and improve generation quality.
- No cold starts for production workflows: Built for responsive, scalable generation with consistent performance.
🛠️ Technical Specifications
| Item | Details |
|---|---|
| Model architecture | Image-to-Video |
| Input | Image URL, Prompt, Negative Prompt, optional Audio URL |
| Output Format | Video |
| Resolution | 720p(default), 1080p |
| Duration | 5s(default), 10s, 15s |
| Shot type | single, multi |
| Prompt expansion | Supported(disabled by default) |
| Seed | Supported; -1 uses a random Seed |
| Audio guidance | Optional Audio URL can be used to guide generation |
| Visual characteristics | Smooth animation, rich color, natural transitions, expressive motion |
| Latency | No fixed latency published; positioned for no cold starts and stable inference |
Sample Prompts
A cinematic slow push-in on a portrait, soft wind moving the hair, warm golden-hour lighting, natural motion, rich color contrastA product shot of a perfume bottle on reflective glass, subtle camera orbit, sparkling highlights, premium advertising styleAn illustrated fantasy city at night, drifting fog, glowing windows, gentle parallax, atmospheric storytelling
💰 Pricing
| Resolution | 5s | 10s | 15s |
|---|---|---|---|
| 720p | $0.50 | $1.00 | $1.50 |
| 1080p | $0.75 | $1.50 | $2.25 |
Billing note: 1080p is priced at a 1.5× multiplier over the 720p rate.
💡 Best Use Cases
- Social media content: Turn cover art, illustrations, or product images into short-form videos for Reels, Shorts, and Stories.
- Marketing and advertising: Produce scalable video creatives from product visuals for campaigns and performance ads.
- Creative storytelling: Extend concept art, portraits, or scene images into cinematic clips with mood and motion.
- Music and art projects: Pair visuals with optional audio guidance to create expressive, rhythm-aware video content.
🔗 Related Models
- Wan 2.6 Image-to-Video Pro: Higher-tier version with 4K support for premium output needs.
- Wan 2.6 Image-to-Video: Standard image-to-video variant.
- Wan 2.6 Text-to-Video: Designed for generating videos directly from text prompts.
Best Practices
- Use clear, well-framed images with a strong subject for more stable and visually convincing motion.
- Write detailed Prompt descriptions covering motion, mood, camera movement, and style.
- Use Negative Prompt to exclude unwanted elements, artifacts, or stylistic outcomes.
- Enable prompt expansion when you want the model to automatically enrich sparse descriptions.
Powiązane modele
xAI Grok Imagine Video v1.5 Image to Video
x-ai/grok-imagine-video-v1.5/image-to-video. Przeglądaj API modeli obrazu, wideo i zamiany twarzy. Wypróbuj model, a następnie zintegruj go przez wspólne REST API.
vidu/q3/image-to-video-spicy
vidu/q3/image-to-video-spicy. Przeglądaj API modeli obrazu, wideo i zamiany twarzy. Wypróbuj model, a następnie zintegruj go przez wspólne REST API.
Vidu Q3 Image To Video
vidu/q3/image-to-video. Przeglądaj API modeli obrazu, wideo i zamiany twarzy. Wypróbuj model, a następnie zintegruj go przez wspólne REST API.

MiniMax H3 Spicy Image to Video
minimax/h3/image-to-video-spicy. Przeglądaj API modeli obrazu, wideo i zamiany twarzy. Wypróbuj model, a następnie zintegruj go przez wspólne REST API.
MiniMax H3 Image to Video
minimax/h3/image-to-video. Przeglądaj API modeli obrazu, wideo i zamiany twarzy. Wypróbuj model, a następnie zintegruj go przez wspólne REST API.
ltx-2.5/image-to-video
ltx-2.5/image-to-video. Przeglądaj API modeli obrazu, wideo i zamiany twarzy. Wypróbuj model, a następnie zintegruj go przez wspólne REST API.
ai/ltx-2.3-spicy/image-to-video-lora
lightricks/ltx-2.3-spicy/image-to-video-lora. Przeglądaj API modeli obrazu, wideo i zamiany twarzy. Wypróbuj model, a następnie zintegruj go przez wspólne REST API.
ai/ltx-2.3-spicy/image-to-video
lightricks/ltx-2.3-spicy/image-to-video. Przeglądaj API modeli obrazu, wideo i zamiany twarzy. Wypróbuj model, a następnie zintegruj go przez wspólne REST API.