ComfyUI Node
Superside Wan 3.0 Reference-to-Video
Wan 3.0 Reference-to-Video on fal. Returns a native VIDEO plus the URL, so SaveVideo or PreviewVideo connects straight in. Endpoints: standard - alibaba/wan-3.0/reference-to-video prime - alibaba/wan-3.0-prime/reference-to-video fal price (2026-10-30): wan-3.0: For every second of video you generate, you will be charged $0.05 480p, $0.10 720p, or $0.20 1080p. For example, a 5s video at 720p will cost $0.50. Pricing is subject to change. | wan-3.0-prime: Billing is calculated per second of video generated: $0.068 at 480p, $0.14 at 720p, or $0.28 at 1080p. For example, a 5-second video at 720p costs $0.70. Pricing is subject to change.
Superside Wan 3.0 Reference-to-Video
- reference_image_1
- reference_image_2
- reference_image_3
- reference_image_4
- reference_video_1
- reference_video_2
- reference_video_3
- reference_video_4
- video
- video_url
◄modelstandard►
◄api_key►
◄prompt►
◄file_url►
◄audiotrue►
◄enable_safety_checkertrue►
◄seed0►
◄reference_audio_urls►
◄duration5►
◄aspect_ratioadaptive►
◄enable_thinkingfalse►
◄resolution1080p►
◄web_url►
◄enable_prompt_expansiontrue►
CategorySuperside
Inputs (22)
| Name | Type | Default | Description |
|---|---|---|---|
| model | COMBO | standard | Which endpoint to call. These share one control surface and differ in quality, speed and price: standard - alibaba/wan-3.0/reference-to-video prime - alibaba/wan-3.0-prime/reference-to-video |
| api_key | STRING | — | |
| promptopt | STRING | Text prompt directing how the reference media is used. Reference media can be addressed positionally, e.g. 'the subject in Image 1 walks past Video 1'. | |
| file_urlopt | STRING | Document URL to base the video on. Requires enable_thinking=true. | |
| audioopt | BOOLEAN | true | Include generated audio. |
| enable_safety_checkeropt | BOOLEAN | true | Enable content moderation for input and output. Disabling it requires account authorization; unauthorized requests are always checked. |
| seedopt | INT | 0-1–2147483647 | -1 = let the model choose. |
| reference_audio_urlsopt | STRING | Up to 5 reference audio URLs totaling at most 15 seconds. One URL per line. | |
| durationopt | INT | 50–30 | Output duration in seconds. Set to null for smart duration, which lets the model pick a length from the prompt and reference media. 0 = let the model choose. |
| reference_image_1opt | IMAGE | Up to 10 reference image URLs. | |
| reference_image_2opt | IMAGE | Up to 10 reference image URLs. | |
| reference_image_3opt | IMAGE | Up to 10 reference image URLs. | |
| reference_image_4opt | IMAGE | Up to 10 reference image URLs. | |
| aspect_ratioopt | COMBO | adaptive | Output aspect ratio, or adaptive selection. |
| reference_video_1opt | VIDEO | Up to 5 reference video URLs totaling at most 15 seconds. Each clip must be at least 16 fps. Input video duration is billed in addition to output duration. | |
| reference_video_2opt | VIDEO | Up to 5 reference video URLs totaling at most 15 seconds. Each clip must be at least 16 fps. Input video duration is billed in addition to output duration. | |
| reference_video_3opt | VIDEO | Up to 5 reference video URLs totaling at most 15 seconds. Each clip must be at least 16 fps. Input video duration is billed in addition to output duration. | |
| reference_video_4opt | VIDEO | Up to 5 reference video URLs totaling at most 15 seconds. Each clip must be at least 16 fps. Input video duration is billed in addition to output duration. | |
| enable_thinkingopt | BOOLEAN | false | Enable enhanced reasoning before generation. |
| resolutionopt | COMBO | 1080p | Output video resolution tier. |
| web_urlopt | STRING | Public webpage URL to base the video on. Requires enable_thinking=true. Only pages that do not require login can be read. | |
| enable_prompt_expansionopt | BOOLEAN | true | Enable intelligent prompt rewriting. Disabling it can save roughly 20-60 seconds of latency but is likely to degrade generation quality. |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| video | VIDEO | — |
| video_url | STRING | — |