luh1124 commited on
Commit
5950889
Β·
1 Parent(s): c98c836

Space: set app_file to app.py (full NeAR); update README notes

Browse files
Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -6,7 +6,7 @@ colorTo: indigo
6
  sdk: gradio
7
  sdk_version: 6.9.0
8
  python_version: "3.10"
9
- app_file: app_gsplat.py
10
  pinned: false
11
  license: apache-2.0
12
  short_description: "Relightable 3D from one image: SLAT, neural renderer, HDRI"
@@ -48,7 +48,7 @@ This repository combines:
48
 
49
  ## ZeroGPU Runtime Notes
50
 
51
- - The Space is temporarily pointed at **`app_gsplat.py`** (gsplat **RGB+ED** raster only) to test JIT / ZeroGPU without NeAR or Hunyuan. Switch **`app_file`** to **`app_hyshape.py`**, **`app.py`**, etc. in the YAML header above as needed.
52
  - **`app_hyshape.py`** (when used as entry): defaults to **`NEAR_HYSHAPE_GEOMETRY_CPU_PRELOAD_AT_START=1`** β€” background **CPU** Hunyuan load at start; **Generate Mesh** pays **GPU move + inference** in `@spaces.GPU`.
53
  - The full `app.py` Space keeps **page-load image defaults** and **HDRI preview** on lightweight CPU paths so the first page visit does not spend the first ZeroGPU allocation on model initialization.
54
  - **`app.py`**: optional background **CPU** preload of Hunyuan + NeAR (`NEAR_MODEL_CPU_PRELOAD_AT_START`); **`@spaces.GPU`** callbacks move each pipeline to CUDA once, then run inference. **gsplat** is used when the pipeline renders (no separate app-level warmup pass).
@@ -102,9 +102,9 @@ Compared with a standard image-to-3D pipeline, NeAR focuses on:
102
  Key files and directories:
103
 
104
  - `example.py` β€” minimal end-to-end inference example.
105
- - `app_gsplat.py` β€” current Hugging Face Space entrypoint (**gsplat-only** ZeroGPU probe).
106
- - `app_hyshape.py` β€” HyShape-only diagnostic; set `app_file: app_hyshape.py` to test Hunyuan geometry in isolation.
107
- - `app.py` β€” full NeAR Gradio app; set `app_file: app.py` in this README to switch back.
108
  - `setup.sh` β€” environment setup helper.
109
  - `checkpoints/` β€” local pipeline configuration and model checkpoints.
110
  - `trellis/pipelines/near_image_to_relightable_3d.py` β€” main NeAR inference pipeline.
 
6
  sdk: gradio
7
  sdk_version: 6.9.0
8
  python_version: "3.10"
9
+ app_file: app.py
10
  pinned: false
11
  license: apache-2.0
12
  short_description: "Relightable 3D from one image: SLAT, neural renderer, HDRI"
 
48
 
49
  ## ZeroGPU Runtime Notes
50
 
51
+ - The Space **`app_file`** in the YAML header above is **`app.py`** (full NeAR app). Switch to **`app_gsplat.py`** or **`app_hyshape.py`** for isolated diagnostics.
52
  - **`app_hyshape.py`** (when used as entry): defaults to **`NEAR_HYSHAPE_GEOMETRY_CPU_PRELOAD_AT_START=1`** β€” background **CPU** Hunyuan load at start; **Generate Mesh** pays **GPU move + inference** in `@spaces.GPU`.
53
  - The full `app.py` Space keeps **page-load image defaults** and **HDRI preview** on lightweight CPU paths so the first page visit does not spend the first ZeroGPU allocation on model initialization.
54
  - **`app.py`**: optional background **CPU** preload of Hunyuan + NeAR (`NEAR_MODEL_CPU_PRELOAD_AT_START`); **`@spaces.GPU`** callbacks move each pipeline to CUDA once, then run inference. **gsplat** is used when the pipeline renders (no separate app-level warmup pass).
 
102
  Key files and directories:
103
 
104
  - `example.py` β€” minimal end-to-end inference example.
105
+ - `app.py` β€” full NeAR Gradio app; default **`app_file`** for the Hugging Face Space (see README YAML header).
106
+ - `app_gsplat.py` β€” **gsplat-only** ZeroGPU probe; set `app_file: app_gsplat.py` to test rasterization in isolation.
107
+ - `app_hyshape.py` β€” HyShape-only diagnostic; set `app_file: app_hyshape.py` for Hunyuan geometry in isolation.
108
  - `setup.sh` β€” environment setup helper.
109
  - `checkpoints/` β€” local pipeline configuration and model checkpoints.
110
  - `trellis/pipelines/near_image_to_relightable_3d.py` β€” main NeAR inference pipeline.