Forward the caller's ZeroGPU token to the conditioner so one request bills as one request

Load the AoTI packages from the public multimodalart/minimax-h3-aoti, move the upsample toggle under the prompt

Migrate to canonical diffusers PR 14371 + public MiniMaxAI/MiniMax-H3 weights, add prompt upsampling toggle

Duration slider from 2s

Mirror the conditioner's canonical table, grouped by ratio

Mirror the conditioner's 16-canvas table (fast 4:3, 3:4 and 21:9 added)

Point at the public multimodalart/qwen3vl-conditioner, called without a token

Fast canvas stays the default; the examples carry full-resolution canvases

Full 16:9 as the default canvas; match the conditioner's renamed fast label

Dynamic GPU duration from the packed sequence, cached examples, torchaudio note

torchaudio for off-rate reference soundtracks; title, fillable width, slot height

Images/audio/video tab order, expandable image slots, native attention for the VAEs

Mirror the generator's title, theme and advanced-options layout

One tab per reference modality, in reading order

MiniMax-H3 ref2va, the denoising half of the split deployment