ProRes 4444 or PNG sequence from AI video: Sume returns MP4
Sume's video jobs return an MP4, not ProRes 4444 or a PNG sequence. Frame stills at times you name come from video frames as images. What to use instead.
Sume does not export ProRes 4444 or a PNG sequence. Its video filter returns a new MP4, and Timeline 1.0 returns one MP4. The nearest thing to a frame sequence is video_frames, which extracts stills from a clip at times you name and returns them as image artifacts.
Runway's changelog (Aug 10, 2026) says Tool Mode and Edit Studio can export Gen-4.5 and Aleph 2 generations as ProRes 4444 with PCM audio or a PNG sequence instead of a compressed MP4. Sume facts are from Video filter, Timeline 1.0 and Video frames, read 2026-10-01.
What does each Sume endpoint return?
| Endpoint | Output |
|---|---|
POST /v1/video-filter | A new MP4 |
POST /v1/timeline-1.0/render | One MP4 |
POST /v1/video-frames | Durable image artifacts at source size, from at[] or fps |
Can video frames stand in for a PNG sequence?
Partly. video_frames takes one media.sume.com clip and a program (at[] or fps), runs asynchronously, and is unbilled. Output is JPEG by default, or PNG with format, with max_edge to clamp size. Each frame is its own artifact rather than a numbered sequence ready for an editor, so check the result before wiring it into a pipeline. There is no audio in those stills. See extract video frames API.
What about long clips?
Video filter sources are capped at 300 seconds. If you need an editing-grade master, export from the tool that makes the source; the HDR and EXR post covers the same boundary for other formats.
What should I do today?
Take the MP4 from a Sume job into your editor, or pull stills with video_frames where a frame-based step is needed. If your pipeline strictly requires ProRes 4444 with PCM audio, Sume is not the tool for that last step.
Sources
Related posts
More in Use cases
- Qwen TTS inline tags vs Sume's emotion and speed controls
Qwen-Audio-3.0-TTS reads tags like [gasp] and [angry] in text. Sume TTS uses generation_config with an emotion guide and speed from 0.6 to 1.5.
- Recraft Crisp Upscale vs Creative Upscale, and Sume's upscale
Recraft's Crisp Upscale enlarges without redrawing; Creative Upscale regenerates. Sume's Image Upscale 1.0 takes an image_url and a factor from 1 to 4.
- Relight a video with AI by API: pixel filters or a prompted edit
Sume has no relight preset. Darken or lift tone with the dim op and exposure or eq filters, or describe new lighting in a video edit prompt. What each can do.
- Resolve Cloud Presentations subtitles: burn cues into a copy
Resolve 21.1 added subtitle support to Cloud Presentations. For a review copy outside Resolve, Sume burns cues onto a video; SRT uploads are unsupported.
Written by Sume