Wan 3.0 Image to Video
Connect a Start Image and describe its motion. Add an End Image to guide the final frame. Auto aspect ratio follows the input framing. This workflow a
Connect a Start Image and describe its motion. Add an End Image to guide the final frame. Auto aspect ratio follows the input framing. This workflow accepts frame images only; use Reference to Video for image, video or audio references.
Use Wan 3.0 for the lower-cost option; Prime offers faster generation with the same controls.
This model is in preview. Results can vary between runs.
Prompt
StringDescribe the scene, movement and sound. Maximum 20,000 characters after resolving reference labels.
Start Image
StringRequired first frame. JPEG, PNG, BMP or WebP; at most 20 MB, 240–8000 pixels per side, no transparency.
End Image
StringOptional final frame. Requires Start Image and the same image limits.
Prompt
StringDescribe the scene, movement and sound. Maximum 20,000 characters after resolving reference labels.
Resolution
StringHigher resolution increases cost.
720pDuration
StringOutput length in seconds. Input video plus output must fit 30 seconds. Auto may use the full remaining duration; its estimate is an upper bound.
5Aspect Ratio
StringAuto chooses framing from the inputs and instruction.
autoGenerate Audio
BooleanInclude generated dialogue, music or sound effects. Turning audio off does not lower the price.
trueEnhance Prompt
BooleanExpand the prompt to add detail. Required for document or webpage references; may increase generation time.
trueAdvanced
ObjectSeed and watermark controls.
falseSeed
NumberUse -1 for a random seed, or 0–2147483647 for a fixed seed. A fixed seed does not guarantee identical results.
-1Watermark
BooleanAdd a visible watermark to the generated video.
falseVideo
InferredGenerated video with embedded audio when enabled.
Nodespell Team
Type
Node
Status
Official
Package
Nodespell AI
Category
AI / Video / AlibabaInput
Output