Wan 3.0 at 30 fps, HappyHorse at 24: set Timeline output.fps
Alibaba lists Wan 3.0 at 30 fps and HappyHorse 1.1 at 24 fps. Joined in Sume's Timeline, a differing output.fps resamples sources and warns; omit it to match.

Alibaba's Model Studio lists Wan 3.0 output as 30 fps MP4 and HappyHorse 1.1 as 24 fps MP4. If you join clips from both in one Sume Timeline render, leave output.fps unset and the render follows the sources; set a value that differs from a source and that source is resampled, with the warning output_fps_resamples_sources.
Vendor specs are from Alibaba's video generation page, read 2026-10-01. Sume's side is from Timeline 1.0 and Timeline compose.
What frame rates does Alibaba list?
| Model id | Duration | Frame rate |
|---|---|---|
wan3.0-video | 2-30s | 30 fps, MP4 |
wan3.0-video-prime | 2-30s | 30 fps, MP4 |
happyhorse-1.1-t2v / -i2v / -r2v | 3-15s | 24 fps, MP4 |
happyhorse-1.0-video-edit | 3-15s | 24 fps, MP4 |
Does Sume list the same models?
Sume lists wan-3.0 (2-30 s at 480p, 720p and 1080p) in its Video Router catalog. The docs read here do not state its output frame rate and HappyHorse is not in the catalog, so the rates above are Alibaba's own figures, not a Sume guarantee. Probe a downloaded clip to confirm; see reading duration, resolution and fps.
What does Timeline do when the rates differ?
The Timeline docs list output.fps as 24, 25, 30 or 60, and say to omit it to match the sources. For Timeline compose, an explicit output.fps that differs from the clip's rate warns output_fps_resamples_sources. The full explanation is in 24 vs 30 fps on Timeline.
Which rate should I pick for a mixed set?
Pick the rate of the clips with the most screen time and leave output.fps unset, or set it once on the final render if a destination requires a rate. Arithmetic, not a docs figure: from 30 to 24 fps about 6 frames per second are dropped, and from 24 to 30 about 6 are repeated. If one clip is the outlier, regenerate it with the model that matches instead of conforming everything.
Sources
Related posts
More in Developers
- Wan 3.0 smart duration and adaptive ratio vs Sume's explicit fields
QwenCloud lists smart duration and adaptive aspect ratio for Wan 3.0. On Sume you send an integer duration and an aspect_ratio the model supports.
- Wan 3.0 sound toggle vs Sume generate_audio for Wan
Wan 3.0 lists a sound toggle at QwenCloud. On Sume, generate_audio defaults to the model's audio capability and some models reject false.
- WhatsApp audio message format: AAC, MP3, OGG Opus mono, 16 MB
WhatsApp accepts AAC, AMR, MP3, M4A and OGG (Opus, mono) up to 16 MB. Sume's audio detach returns mp3 or wav, so mp3 fits; ogg needs another tool.
- WhatsApp Cloud API video message size limit: 16 MB, H.264 and AAC
WhatsApp video messages take MP4 or 3GP up to 16 MB, H.264 video and AAC audio only. See what Sume's exact trim outputs and what you still check yourself.
Written by Sume