Update README.md

README.md

@@ -52,13 +52,39 @@ In stage one, the model is pretrained using the [LAION-COCO](https://huggingface
 
 ## ▶️ Running the Models
 
+First install [PyTorch](https://pytorch.org) according to the instructions specific to your operating system. For AMD GPUs, you can aslo start with a [rocm/pytorch](https://hub.docker.com/r/rocm/pytorch/tags?name=pytorch) docker.
+
+To install the recommended packages, run: 
+
+```bash
+git clone https://github.com/AMD-AIG-AIMA/Instella-T2I.git
+cd Instella-T2I
+# install Flash-Attention on MI300X
+GPU_ARCH=gfx942 MAX_JOBS=$(nproc) pip install git+https://github.com/Dao-AILab/flash-attention.git -v
+# install other dependencies
+pip install -r requirements.txt
+```
+
+## ▶️ Running the Tests
+
 Using provide `test_diff.py` and `test_ar.py` to run image generation in interactive mode for the diffusion and AR models.
 
-Please make sure model checkpoints are placed under the `checkpoints` folder, otherwise please specify `--ckpt_path=YOUR_MODEL_PATH` and `--bae_path=YOUR_BAR_PATH`.
+The inference scripts will automatically download the checkpoints to path specified by `--ckpt_path`.
+
+```bash
+python test_diff.py --ckpt_path DESIRED_PATH_TO_MODELS
+python test_ar.py --ckpt_path DESIRED_PATH_TO_MODELS
+```
+
+#### Specifying hyperparameters
+To specify hyperparameters, run:
 
 ```bash
-python test_diff.py 
-python test_ar.py 
+python test_diff.py \
+    --ckpt_path DESIRED_PATH_TO_MODELS \
+    --cfg_scale 9.0 \
+    --temp 0.8 \
+    --num_steps 50 \
 ```
 
 #### Specifying hyperparameters