ui: move vid_roll to top-right row, restore vid_hdri below vid_cam

ui: remove PBR GLB export from online demo

perf(glb): further reduce bake params to avoid 120s timeout

perf(glb): speed up bake by reducing hardcoded defaults

revert: disable NeAR main-process preload; restore torchvision weights=...

ui: update title and description

chore: bump default video frames back to 48, step 2

fix(app): remove @torch .no_grad from generate_glb

fix: enable NeAR CPU preload by bypassing torchvision weights CUDA init

fix(app): split renderings into two @GPU callbacks; lower defaults

fix(app): do NOT preload NeAR in main process; warm disk caches only

fix(app): lazy-import trellis, preload NeAR on CPU, fix ZeroGPU duration

fix: replace DINOv2 torch.hub.load with download_url_to_file in preload

fix: use @GPU (no duration) for geometry and slat, matching app_hyshape.py

fix: increase GPU lease duration and reduce Hunyuan3D inference steps

fix: pre-cache RMBG-2.0 and DINOv2 in preload worker to prevent GPU lease timeout

fix: enable gradients for texture baking in GLB export

fix: restore clear_cache function definition

refactor: merge ③④ GPU callbacks for ZeroGPU stability

fix(preload): match app_hyshape.py — load Hunyuan3D to CPU RAM, cache NeAR to disk

fix(zerogpu): remove _MODEL_LOCK from GPU callbacks; preload = disk cache only

fix(preload): split into disk-cache phase + CPU-load phase to unblock GPU callbacks

fix(zerogpu): skip NeAR CPU preload — BiRefNet/DINOv2 init triggers CUDA

refactor(app): ZeroGPU-safe 4-step pipeline with Hunyuan PBR GLB export

fix(zerogpu): add explicit duration, disable geometry offload by default

fix(zerogpu): remove stale CUDA flags, enable CPU preload by default

fix(near): defer renderer/tone-mapper init to first GPU ensure

refactor(app): ZeroGPU-oriented NeAR UI; path-only SLaT; dual videos

Space: move pipelines to CUDA only when spaces SDK is present

Gradio: apply NEAR_GRADIO_THEME (blue) to Blocks

HF Space: load pipelines before module-level demo, fix import entry

Space app: SLaT session cache, tone-mapper safety, CUDA/inference fixes

feat(app): block Gradio bind until CPU weights load (no background preload)

fix(spaces): Hdri torch.load after ConvNeXt; default off CPU preload with spaces

fix(load): CPU-only checkpoint load for ZeroGPU main process

app: CPU preload Hunyuan+NeAR, cuda move in GPU callbacks; drop gsplat warmup

fix(gsplat): prebuilt wheel in requirements + NEAR_GSPLAT_WHEEL_URL

fix(space): split ZeroGPU cold-start paths and add timing diagnostics

refactor: use bare spaces.GPU like E-RayZer (drop per-callback duration)

feat: optional gsplat source install + RGB+ED warmup (E-RayZer-style)

fix(space): longer ZeroGPU budget for gsplat JIT + video (ceiling 90s, duration=120 cap)

perf: parallel Hunyuan+NeAR load by default, per-branch timing logs

fix(ui): pass Gradio 6 theme/css via launch() for HF Spaces

fix(space): avoid deleting Gradio cache and tmp_gradio paths still in UI

feat(space): background prune stale tmp_gradio session dirs by age

fix(space): mirror Space secret 'near' into HF_TOKEN for gated Hub models

fix(pipeline): respect pretrained rembg (RMBG-2.0); optional NEAR_REMBG_MODEL

ZeroGPU: init duration before import spaces; default 60s; strip env > ceiling

ZeroGPU: default ceiling 120s, clamp explicit duration; env NEAR_ZEROGPU_HF_CEILING_S

ZeroGPU: hard clamp duration to 300s (ignore env 1800)