Add the lightx2v Minimax-h3-Turbo LoRA as a per-request alternative

Default steps 4 -> 6

Switch to the recommended ckpt850 EMA LoRA; default steps back to 4

Default steps 6 -> 8 (better quality at the ckpt500 weights)

Default to the ckpt500 turbo weights, add a per-request LoRA toggle

Rebuild the UI as a custom studio frontend on gradio.Server

Fold the 4-step Turbo LoRA into the transformer, default to 4 steps

Cache the conditioner client with functools.cache, tidy comments

Let gradio_client forward the caller's ZeroGPU token itself instead of pinning one by hand

Bill the conditioner call to the requesting user's own ZeroGPU token, never an org token

Pay for the conditioner call with the first ZeroGPU identity that can: the caller's token, this Space's HF_TOKEN, then none

Fall back to an anonymous conditioner call when the forwarded ZeroGPU token is refused

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

Update README.md

Demo short description

Rename to MiniMax H3

Wire the AoTI load path (env-gated) and the sub-768p canvases

Sync the split MiniMax-H3 Spaces

Sync the split MiniMax-H3 Spaces

Sync the split MiniMax-H3 Spaces

Sync the split MiniMax-H3 Spaces

initial commit