ai/wan-2.2-spicy/image-to-video-lora

alibaba/wan-2.2-spicy/image-to-video-lora

Generate AI videos with personalized styles using LoRA. Upload images and apply a trained style model to WAN 2.2 — create unique, stylized videos with consistent visual identity.

Examples

ai/wan-2.2-spicy/image-to-video-lora Examples 1

Parameters

NameTypeDefaultConstraintsDescription
prompt *Prompttextarea—≤ 5000 charsThe positive prompt for the generation.
image *Imageimage_upload—image/* · 1–1 itemsThe image for generating the output.
resolutionResolutionselect480p480p | 720pThe resolution of the generated media.
durationDurationselect55 | 8The duration of the generated media in seconds.
lorasLorasarray<object>—0–3 itemsList of LoRAs to apply (max 3).
↳path *Pathtext—≤ 500 charsURL or the path to the LoRA weights.
↳scaleScaleslider10 ~ 4 · step 0.1The scale of the LoRA weights. This is used to scale the LoRA weight before merging it with the base model.
high_noise_lorasHigh Noise Lorasarray<object>—0–3 itemsList of high noise LoRAs to apply (max 3).
↳path *Pathtext—≤ 500 charsURL or the path to the LoRA weights.
↳scaleScaleslider10 ~ 4 · step 0.1The scale of the LoRA weights. This is used to scale the LoRA weight before merging it with the base model.
low_noise_lorasLow Noise Lorasarray<object>—0–3 itemsList of low noise LoRAs to apply (max 3).
↳path *Pathtext—≤ 500 charsURL or the path to the LoRA weights.
↳scaleScaleslider10 ~ 4 · step 0.1The scale of the LoRA weights. This is used to scale the LoRA weight before merging it with the base model.
seedSeednumber——The random seed to use for the generation. -1 means a random seed will be used.

Output fields

FieldTypeDescription
videosarray<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/wan-2.2-spicy/image-to-video-lora" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "input": {
    "prompt": "Animate the subject with natural motion, a gentle camera orbit, cinematic lighting, and smooth temporal consistency.",
    "image": [
      "https://assets-public.namifusion.com/marketplace/images/2026-06-12/638e1ee18ac7.jpeg"
    ],
    "resolution": "480p",
    "duration": 5
  }
}'

# 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-2.2-spicy/image-to-video-lora",
    headers=HEADERS,
    json={
        "input": {
            "prompt": "Animate the subject with natural motion, a gentle camera orbit, cinematic lighting, and smooth temporal consistency.",
            "image": [
                "https://assets-public.namifusion.com/marketplace/images/2026-06-12/638e1ee18ac7.jpeg"
            ],
            "resolution": "480p",
            "duration": 5
        }
    },
)
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-2.2-spicy/image-to-video-lora", {
  method: "POST",
  headers: { ...HEADERS, "Content-Type": "application/json" },
  body: JSON.stringify({
    "input": {
      "prompt": "Animate the subject with natural motion, a gentle camera orbit, cinematic lighting, and smooth temporal consistency.",
      "image": [
        "https://assets-public.namifusion.com/marketplace/images/2026-06-12/638e1ee18ac7.jpeg"
      ],
      "resolution": "480p",
      "duration": 5
    }
  }),
});
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

ai/wan-2.2-spicy/image-to-video-lora

Turn a single image into a stylized video with LoRA-powered visual consistency.

ai/wan-2.2-spicy/image-to-video-lora is an image-to-video model built for personalized style generation on top of WAN 2.2. By combining an input image with one or more LoRA models, it enables creators to produce short videos with a more distinctive and consistent visual identity, making it well suited for branded content, character-driven media, and stylized creative workflows.

🚀 Key Features

  • LoRA-based style control: Apply trained LoRA models to inject specific artistic styles, brand aesthetics, or character looks into generated videos.
  • Image-to-video generation: Animate a single input image into a short video clip, ideal for turning static assets into motion content.
  • Multi-LoRA support: Use standard, high-noise, and low-noise LoRA configurations for more granular control over style behavior.
  • Consistent visual identity: Designed for workflows that require a stable look across scenes, campaigns, or recurring characters.
  • Flexible output options: Supports 480p and 720p output, with 5-second and 8-second durations to balance speed and quality.
  • Seed-based reproducibility: Set a Seed for repeatable experiments, controlled iteration, and easier prompt tuning.

🛠️ Technical Specifications

ItemDetails
Model architectureWAN 2.2 image-to-video with LoRA style enhancement
Task typeImage-to-video
Input formatPrompt, Image, LoRA model lists
Output formatVideo
Resolution480p(default), 720p
Duration5s(default), 8s
Frame rateNot publicly specified; optimized for short-form video generation
Style controlSupports loras, high_noise_loras, and low_noise_loras, up to 3 per category
SeedSupported; -1 uses a random Seed
LatencyDepends on Resolution, Duration, and LoRA configuration complexity
Best input assetsPortraits, product images, illustrations, concept art, branded visuals

Sample Prompts

  • A cinematic slow turn of the subject, subtle camera push-in, dramatic lighting, rich detail, consistent stylized look
  • Transform this product image into a premium ad video, soft camera motion, clean background, emphasize material quality and brand identity
  • Animate this illustration into a dreamy fantasy clip, natural character motion, cohesive colors, smooth visual flow

💰 Pricing

ItemPrice
Base Price$0.20 / run

💡 Best Use Cases

  • Brand marketing: Convert product shots, key visuals, or campaign assets into short branded videos with a unified style.
  • Social media content: Create stylized clips for TikTok, Instagram Reels, and other short-form platforms.
  • Character and IP development: Extend character artwork or concept images into animated content while preserving visual identity.
  • Creative studio workflows: Useful for style exploration, pitch materials, and rapid visual prototyping.

🔗 Related Models

  • WAN 2.2 base image-to-video variants: A good alternative if you need general-purpose animation without LoRA-based style customization.
  • LoRA-enhanced creative workflows: This version is especially valuable when brand consistency, character continuity, or stylized output is a priority.

Related models

xAI Grok Imagine Video v1.5 Image to Video
Image to VideoX Ai

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.

from $0.850 / per run
vidu/q3/image-to-video-spicy
Image to VideoVidu

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.

from $0.750 / per run
Vidu Q3 Image To Video
Image to VideoVidu

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.

from $0.750 / per run
MiniMax H3 Spicy Image to Video
Image to VideoMinimax

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.

from $0.200 / per run
MiniMax H3 Image to Video
Image to VideoMinimax

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.

from $0.650 / per run
ltx-2.5/image-to-video
Image to VideoLtx 2.5

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.

from $0.500 / per run
ai/ltx-2.3-spicy/image-to-video-lora
Image to VideoLightricks

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.

from $0.150 / per run
ai/ltx-2.3-spicy/image-to-video
Image to VideoLightricks

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.

from $0.100 / per run
ai/wan-2.2-spicy/image-to-video-lora API — Price, See playground & Documentation | NamiFusion