aidlab/design2garmentcode-impl
7
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

modify readme

Browse Source
This commit is contained in:
sky
2025-07-03 17:16:01 +08:00
parent 89766fe3d1
commit 0d99ae9d7c
1 changed files with 8 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
README.md
View File

@@ -43,13 +43,14 @@ Follow the steps **in the given order**:
export OPENAI_API_KEY="sk‑..." export OPENAI_API_KEY="sk‑..."
``` ```
- **Edit `system.json`** (project root) – manually specify `api_key`, `base_url`, and `model` if you prefer a file‑based approach. - **Edit `system.json`** (project root) – manually specify `api_key`, `base_url`, and `model` if you prefer a file‑based approach.
2. **You should first download the base model** 2. **Download the required models**:
[`Qwen2-VL-2B-Instruct`]<https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct/tree/main> - First, download the base model [Qwen2-VL-2B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct/tree/main).
and place its full folder in: Place the entire folder at:
`lmm_utils/Qwen/Qwen2-VL-2B-Instruct/` `lmm_utils/Qwen/Qwen2-VL-2B-Instruct/`
Then make sure that [`model.pth`]<lmm_utils/Qwen/qwen2vl_lora_mlp/model.pth> is placed in the `lmm_utils/Qwen/qwen2vl_lora_mlp/` directory. - Next, download the fine-tuned weights file [model.pth](lmm_utils/Qwen/qwen2vl_lora_mlp/model.pth),
This file contains the LoRA+MLP fine-tuned weights. and place it in:
`lmm_utils/Qwen/qwen2vl_lora_mlp/`
--- ---
## Quick GUI Demo ## Quick GUI Demo
@@ -106,7 +107,7 @@ Once a pattern is generated in GUI, you can refine them directly inside the GUI:
### 1. Generate from a pattern.json ### 1. Generate from a pattern.json
After generating the pattern data, you can simulate the corresponding 3D output directly from the pattern's JSON file. After generating the pattern data, you can simulate the corresponding 3D output directly from the pattern's JSON file.
```bash ```bash
python lmm_utils/test_garment_sim.py --pattern_spec $OUTPUT_JSON python test_garment_sim.py --pattern_spec $INPUT_JSON
``` ```
### 2. Generate from gui ### 2. Generate from gui
You can also run the simulation directly on the GUI to obtain 3D data. You can also run the simulation directly on the GUI to obtain 3D data.