FastFrames-L vs Viggle Remake
Newest: Viggle Remake · Widest inputs: Viggle Remake · Native audio: Native audio unconfirmed. Not enough arena votes yet for a quality score, so this is a spec comparison.
Apple
FastFrames-L
- Arena—
- From—
- Max length—
Viggle AI
Viggle Remake
- Arena—
- From—
- Max length—
Add a model
Make it a three-way comparison.
Where they differ
Quality is the arena score from blind, side-by-side human votes. Price, length and resolution come from each lab’s own listings.
- NewestViggle RemakeFastFrames-L Nov 2026 · Viggle Remake Nov 2, 2026
- Widest inputsViggle RemakeFastFrames-L: Text prompts · Viggle Remake: Text prompts, Reference images, Video
- Native audioNative audio unconfirmedGenerates an audio track with the video: FastFrames-L unconfirmed · Viggle Remake unconfirmed
- Image to videoViggle RemakeStarts from an uploaded image: FastFrames-L no · Viggle Remake yes
- Self-hostingAll open weightsDownloadable weights (MiniMax H3 Community License)
- Most API hostsSame reachFastFrames-L: 0 · Viggle Remake: 0
Every spec in one table
Dashes mean the data is not published.
| Specification | ||
|---|---|---|
| Task | Text-to-video generation | Video-to-video editing |
| Published capabilities | Two-step autoregressive video diffusion model for generating 480p frames at interactive latency. | Edits people, objects or scenery in source footage. Two LoRA modes run on the MiniMax H3 transformer. |
| Model size | 14B parameters | — |
| Access | Downloadable checkpoints with Apple inference code | Viggle app and downloadable editing adapters |
| Result | — | Edited video retaining the source motion and soundtrack |
| Operating limits | Reference implementation renders 832 × 480 video at 16 fps, with 81 frames in the published example. | — |
| Sources | Publisher documentation · Model weights | Model weights · Additional documentation |
| Output | ||
| Produces | Video | Edited video retaining the source motion and soundtrack |
| Resolutions | 480p | — |
| Highest resolution | 480p | — |
| Inputs | ||
| Text prompts | Yes | Yes |
| Start image (image to video) | No | Yes |
| Video input | No | Yes |
| Audio input | No | No |
| Access | ||
| Weights | Open | OpenMiniMax H3 Community License |
| Released | Nov 2026 | Nov 2, 2026 |
Which should you choose?
Which is better, FastFrames-L or Viggle Remake?
Neither model has enough arena votes for a reliable quality score yet, so this page compares specs only. Run the same three or four prompts through each and judge the results.
What is the difference between FastFrames-L and Viggle Remake?
FastFrames-L is a video model from Apple (Nov 2026), taking text prompts and producing video. Viggle Remake is a video model from Viggle AI (Nov 2, 2026), taking text prompts, reference images and video and producing edited video retaining the source motion and soundtrack.
Which is newer?
FastFrames-L Nov 2026; Viggle Remake Nov 2, 2026.
Which generates video with sound?
Generates an audio track with the video: FastFrames-L unconfirmed; Viggle Remake unconfirmed.
Can I run any of these on my own hardware?
All open weights. Downloadable weights (MiniMax H3 Community License).