Wan 3.0 Image-to-Video Spicy API

Wan 3.0 is Alibaba's Tongyi Lab's next-generation video generation model officially released on August 24, 2026. This document covers its Image-to-Video Spicy endpoint: generating high-quality video from reference images plus text prompts, with first-frame image animation, native synchronized audio, and multilingual dubbing. Spicy mode is the uncensored global variant of Wan 3.0 — it removes standard content restrictions while preserving the same generation capabilities, offering greater creative freedom.

On iCreat, developers call the aliyun/wan3-0/image-to-video-global endpoint through an asynchronous task-based REST API. Pricing: 480P $0.05/sec, 720P $0.10/sec, 1080P $0.20/sec, billed by output duration.

Model Positioning

Wan 3.0 Image-to-Video Spicy targets uncensored image-driven video creation — the Spicy global I2V endpoint of Wan 3.0. Unlike T2V Spicy (pure text-to-video), it accepts reference images as input, animating static images into dynamic video with native synchronized audio. Spicy removes the standard version's content moderation, making it suitable for advertising, art, and concept design that demand freer creative expression. Single-pass duration 4–15 seconds, supporting 720P and 1080P.

Core Capabilities

First-frame image animation

Pass a reference image via the media array (type: reference_image); the model uses the image as a starting point to generate dynamic video, preserving the original subject structure and style, giving static images dynamic life.

Native synchronized audio

Audio is generated in the same pass as the video (not added in post), including dialogue, BGM, and sound effects, ensuring temporal alignment between sound and motion. Supports multilingual dubbing.

Real-world fidelity

Significant improvements in micro-expressions, body linkage, spatial layout, physical motion, and on-screen text rendering, reducing the "AI feel" for a real-shot look.

Negative prompts

Supports negative_prompt to describe content that should not appear in the video, improving generation control.

Thinking mode

Optional reasoning mode — the model reasons about composition and motion before generating, suited for multi-event sequences and complex compositions.

Pricing

Total = unit price × output video duration. Billed by actual generated duration with no minimum-length threshold.

Note: The resolution parameter accepts 720P and 1080P; the 480P price is listed for reference only, subject to platform support. Alibaba Cloud Bailian domestic list price: 480P ¥0.3/sec, 720P ¥0.6/sec, 1080P ¥1.2/sec.

Use Cases

• E-commerce product display: turn product images into showcase videos with audio
• Advertising and TVC: animate storyboard frames into dynamic ad previews
• Short-video and social media: batch image-to-video production with controlled per-clip cost
• Character animation: generate dynamic shots from character references, preserving subject consistency
• Uncensored free creative: advertising, art, and concept design under Spicy mode
• Creative concept validation: image-driven rapid scene dynamic testing

Model Comparison

Wan 3.0 I2V Spicy vs. Wan 3.0 I2V (Standard)

Wan 3.0 I2V Spicy vs. Wan 3.0 T2V Spicy and HappyHorse 1.1

Why Choose Wan 3.0 I2V Spicy?

• Uncensored free editing: Spicy mode removes content restrictions for advertising, art, and concept design I2V
• First-frame image animation: static image to dynamic video with native audio in one pass, preserving subject consistency
• Native synchronized audio: dialogue, BGM, and sound effects in one pass, no post-production dubbing
• Transparent per-second billing: 720P $0.10/sec, 1080P $0.20/sec, predictable cost
• Real-world fidelity: micro-expressions, body linkage, and physics significantly improved
• Negative prompt control: exclude unwanted content for better generation control

Specifications

Architecture

Wan 3.0 uses a unified model architecture, consolidating text-to-video, image-to-video, and reference-to-video into a single system. The model introduces an "Omni-Reference" system supporting diverse reference assets (text, images, video, audio, documents, web pages) for high-fidelity video synthesis. Audio is generated in the same pass as the video, ensuring temporal alignment. The I2V endpoint receives reference images via the media array; the model animates from the image as a starting point, preserving subject structure and style. Spicy mode removes the standard version's content moderation filter at the review layer, preserving the same generation backbone and reasoning capabilities.

Wan 3.0 entered public beta on August 6, 2026, and launched commercially on August 24. Unlike the open-source Wan 2.2 series, Wan 3.0 is a closed-source API model with no weight downloads.

Notes

• duration must be an integer between 4 and 15; out-of-range values return an error (I2V endpoint max is 15 seconds, shorter than T2V's 30 seconds)
• prompt is required; negative_prompt is optional, used to exclude unwanted content
• media[].type should use reference_image for reference images
• The resolution parameter accepts 720P and 1080P; the 480P price listed in the pricing table is for reference only, subject to platform support
• 1080P costs more per second than 720P; estimate cost in advance for long videos (total = unit price × duration)
• Native audio is default output, including dialogue, BGM, and sound effects, synchronized with visuals
• Spicy mode is uncensored; generated content is not subject to the standard version's content restrictions — comply with local laws and regulations when using
• Fetch results via the result endpoint promptly after completion
• Wan 3.0 is a closed-source API model, not supporting local deployment; for self-hosting, use the open-source Wan 2.2 series