Transform your 3D texturing workflow with the power of generative AI, directly within Blender!
update trellis.2 download size to ~20.4 GB
sakalond1ba2323c4ebb
diff --git a/README.md b/README.mdindex 996fcdb..6f3451a 100644--- a/README.md+++ b/README.md@@ -358,7 +358,7 @@ The `installer.py` script (found in this repository) automates the download and| 5 | Qwen Core | Qwen Image Edit texturing architecture | ~20.3 GB || 6 | Qwen + Lightning LoRAs | Qwen with additional Lightning LoRAs | ~22.6 GB || 7 | Qwen Nunchaku | Qwen with Int4 quantized Nunchaku model (lower VRAM) | ~33.0 GB |-| 8 | TRELLIS.2 | Image/text-to-3D mesh generation (models auto-download on first use) | ~0.1 GB |+| 8 | TRELLIS.2 | Image/text-to-3D mesh generation (~5 GB install + ~15.4 GB models on first use) | ~20.4 GB || 9 | Marigold IID | PBR decomposition node (models auto-download on first use) | ~0.01 GB || 10 | StableDelight | Specular-free albedo for PBR (includes model download) | ~3.3 GB || 11 | FLUX.2 Klein *(experimental)* | Klein texturing architecture (~13 GB VRAM required) | ~12.4 GB |@@ -370,7 +370,7 @@ The `installer.py` script (found in this repository) automates the download and- **Texturing only (Qwen):** Option 5 (or 6/7)- **Add PBR to any setup:** Options 9 + 10 (included in options 3 and 4)-> **Note:** Some packages (TRELLIS.2, Marigold IID) download additional models automatically on first use via ComfyUI. Expect extra downloads the first time you run these features.+> **Note:** TRELLIS.2 and Marigold IID download additional models automatically on first use via HuggingFace. The sizes shown above include these first-use downloads. Expect the initial run to take longer.4. **Restart ComfyUI:** If ComfyUI was running, restart it to load new custom nodes.*(For manual dependency installation-including FLUX.1-dev and Qwen Image Edit setups-see `docs/MANUAL_INSTALLATION.md`.)*diff --git a/installer.py b/installer.pyindex a4d80e6..abf3ec1 100644--- a/installer.py+++ b/installer.py@@ -708,8 +708,9 @@ MENU_PACKAGES: Dict[str, Dict[str, Any]] = {"description_suffix": "*Installs Qwen Core components plus Nunchaku nodes and the Int4 quantized model (12.7GB).*"},'8': {"name": "[TRELLIS.2] Image-to-3D Node","tags": ["trellis2"],- "size_gb": 0.1,- "description_suffix": "*Installs ComfyUI-TRELLIS2 custom node. Models are downloaded automatically on first use by the node.*\n"+ "size_gb": 20.4,+ "description_suffix": "*Installs ComfyUI-TRELLIS2 custom node + isolated Python environment (~5 GB).*\n"+ " *TRELLIS.2 models (~15.4 GB) are downloaded automatically from HuggingFace on first use.*\n"" *LICENSE NOTICE: Only the 'Native (TRELLIS.2)' texture mode uses nvdiffrast/nvdiffrec*\n"" *(NVIDIA Source Code License — non-commercial use only). See README.md for full details.*",},