Commit History
-
Add the lightx2v Minimax-h3-Turbo LoRA as a per-request alternative
h3_lora.py now loads both turbo LoRAs and switches the folded set in place per request (unfold old / fold new, one bf16 rounding, AoTI-safe). The lightx checkpoint is PEFT-style against the diffusers tree (rank 128, alpha 8 -> fold scale 0.0625); the larry one keeps the reference key conversion. The UI checkbox becomes a LoRA dropdown (larry / lightx / off) that suggests each design point in steps (6 / 4 / 28), and the API gains a 'lora' string parameter — the legacy use_lora bool still works.456aa27
-
Mobile-friendly layout, all features kept
Stage moves above the control deck on narrow screens, the deck becomes a full-width scrolling panel with a sticky Generate button, the transport bar wraps with the progress bar on its own row, the header collapses to logo + status pill, dropzones/sliders get bigger touch targets, and inputs use 16px to stop iOS focus zoom.25c3db5 -
Default steps 4 -> 6
942d78c -
Switch to the recommended ckpt850 EMA LoRA; default steps back to 4
ckpt850 is the final checkpoint of the round and sharp at 4 steps per the updated card, so the UI/API default drops 8 -> 4. Also adds H3_LORA_STRENGTH (default 1.0), the card's sharpness/artifact dial, applied at fold time and in the per-request toggle.4512613 -
Default steps 6 -> 8 (better quality at the ckpt500 weights)
e35aff5 -
Fix LoRA toggle (zip misuse made converted a tuple), add a queue/ETA progress bar
set_enabled now iterates _delta_targets directly. The frontend uses client.submit with data+status events: the transport bar shows queue position, then fills against the queue's ETA blended with the elapsed timer, indeterminate while conditioning.90627fd -
Default to the ckpt500 turbo weights, add a per-request LoRA toggle
- H3_LORA default is now minimax_h3_turbo_4step_ckpt500.safetensors, the model card's recommended default (newest, sharpest, non-EMA) - the low-rank factors stay resident after the startup fold, so h3_lora.set_enabled() folds/unfolds B@A in place per request; the AoTI blocks read the same live storage. UI gets a 'Turbo LoRA' checkbox (default on), the API a use_lora parameter (default true) - default steps 4 -> 6 per the card's updated guidance (comfort zone is 6-8 at this checkpoint; 4 is softer)868ff3a -
Back to @gradio/client: ZeroGPU requires its HF iframe auth headers
The Server-mode docs are explicit that plain fetch/EventSource calls do not forward the iframe auth headers ZeroGPU quota handling needs, so bookings landed on the pod IP's shared quota. The earlier fn_index crash was a stale tab from the pre-Server build. Keeps the tuple unwrap and FileData path fallback.d82c64a -
Call the v2 named-endpoint API directly, unwrap the single-Api-output tuple
- @gradio/client resolves a legacy fn_index that Server mode's internal Blocks does not have (KeyError on queue join); the v2 API (POST /gradio_api/call/v2/generate + SSE) addresses endpoints by name - the tuple return is one 'Api' output, so it arrives nested one level - whitelist OUTPUT_DIR for the /gradio_api/file= routee6d78bd -
Resolve returned FileData without a url through /gradio_api/file= (Server mode can return only path)
97f8752 -
Rename /config to /studio-config: Gradio's own client-discovery route lives at /config, and shadowing it broke @gradio/client ('Could not get API info')
b84671f -
Rebuild the UI as a custom studio frontend on gradio.Server
Server mode: @app.api(name="generate") keeps the queue / ZeroGPU / gradio_client contract (same name and signature), @app.get("/") serves a self-contained index.html — dark studio layout with a control deck (prompt, keyframe dropzones, canvas / duration / steps / seed), a preview monitor, and a transport-style report bar, driven by the @gradio/client JS package. /status and /config feed the readiness pill and the canvas list. Keyframe cover-crop moved server-side into generate so API callers get it too.299d59b