ZMIME
Video model comparison · 2 models · Updated Nov 21, 2026

H3-Tiny-17B-Pruned-Ref2VA vs Viggle Remake

Newest: H3-Tiny-17B-Pruned-Ref2VA · Widest inputs: Viggle Remake · Native audio: H3-Tiny-17B-Pruned-Ref2VA. Not enough arena votes yet for a quality score, so this is a spec comparison.

  1. H3-Tiny

    H3-Tiny-17B-Pruned-Ref2VA

    Released Nov 19, 2026

    • Text to video
    • Image to video
    • Native audio
    • Arena—
    • From—
    • Max length—
  2. Viggle AI

    Viggle Remake

    Released Nov 2, 2026

    • Video-to-video editing
    • Arena—
    • From—
    • Max length—
  3. Add a model

    Make it a three-way comparison.

01 — At a glance

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.

  • NewestH3-Tiny-17B-Pruned-Ref2VAH3-Tiny-17B-Pruned-Ref2VA Nov 19, 2026 · Viggle Remake Nov 2, 2026
  • Widest inputsViggle RemakeH3-Tiny-17B-Pruned-Ref2VA: Text prompts, Reference images · Viggle Remake: Text prompts, Reference images, Video
  • Native audioH3-Tiny-17B-Pruned-Ref2VAGenerates an audio track with the video: H3-Tiny-17B-Pruned-Ref2VA yes · Viggle Remake unconfirmed
  • Image to videoBoth animate imagesStarts from an uploaded image: H3-Tiny-17B-Pruned-Ref2VA yes · Viggle Remake yes
  • Self-hostingAll open weightsDownloadable weights (MiniMax H3 Community License)
  • Most API hostsSame reachH3-Tiny-17B-Pruned-Ref2VA: 0 · Viggle Remake: 0
02 — Side by side

Every spec in one table

Dashes mean the data is not published.

H3-Tiny-17B-Pruned-Ref2VA vs Viggle Remake specifications side by side
SpecificationH3-Tiny-17B-Pruned-Ref2VAH3-TinyViggle RemakeViggle AI
TaskAudiovisual generationVideo-to-video editing
Published capabilitiesGenerates video and synchronized sound from reference imagery using a pruned MiniMax H3 transformer.Edits people, objects or scenery in source footage. Two LoRA modes run on the MiniMax H3 transformer.
Model size17.07B transformer parameters—
AccessDownloadable transformer checkpoint for the H3 pipelineViggle app and downloadable editing adapters
Result—Edited video retaining the source motion and soundtrack
Operating limits50 steps—
SourcesModel weightsModel weights · Additional documentation
Output
ProducesVideo with soundEdited video retaining the source motion and soundtrack
SoundAlways generated—
Inputs
Text promptsYesYes
Start image (image to video)YesYes
Video inputNoYes
Audio inputNoNo
Access
WeightsOpenMiniMax H3 Community LicenseOpenMiniMax H3 Community License
ReleasedNov 19, 2026Nov 2, 2026
03 — Questions

Which should you choose?

Which is better, H3-Tiny-17B-Pruned-Ref2VA 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 H3-Tiny-17B-Pruned-Ref2VA and Viggle Remake?

H3-Tiny-17B-Pruned-Ref2VA is a video model from H3-Tiny (Nov 19, 2026), taking text prompts and reference images and producing video with sound. 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?

H3-Tiny-17B-Pruned-Ref2VA Nov 19, 2026; Viggle Remake Nov 2, 2026.

Which generates video with sound?

Generates an audio track with the video: H3-Tiny-17B-Pruned-Ref2VA yes; Viggle Remake unconfirmed.

Can I run any of these on my own hardware?

All open weights. Downloadable weights (MiniMax H3 Community License).