Update README.md

README.md

@@ -1,5 +1,5 @@
 ## Prompt-Diffusion: In-Context Learning Unlocked for Diffusion Models
-### [Project Page](https://zhendong-wang.github.io/prompt-diffusion.github.io/) | [Paper](https://arxiv.org/abs/2305.01115)
+[Project Page](https://zhendong-wang.github.io/prompt-diffusion.github.io/) | [Paper](https://arxiv.org/abs/2305.01115) | [GitHub](https://github.com/Zhendong-Wang/Prompt-Diffusion)
 ![Illustration](./assets/teaser_img.png)
 
 **In-Context Learning Unlocked for Diffusion Models**<br>
@@ -18,56 +18,8 @@ Our model also shows compelling text-guided image editing results. Our framework
 
 ![Illustration](./assets/illustration.png)
 
-## ToDos
-- [x] Release pretrained models
-- [x] Release play-around codes
-
-
-## Results
-### Multi-Task Learning
-
-![Illustration](./assets/multi_task_results.png)
-
-### Generalization to New Tasks
-
-![Illustration](./assets/generalization_results.png)
-
-### Image Editing Ability
-
-![Illustration](./assets/edit_results.png)
-
-## Train Prompt Diffusion
-
-### Prepare Dataset
-
-We use the public dataset proposed by [InstructPix2Pix](https://github.com/timothybrooks/instruct-pix2pix) as our base dataset, 
-which consists of around 310k image-caption pairs. Furthermore, we apply the [ControlNet](https://github.com/lllyasviel/ControlNet) annotators
-to collect image conditions such as HED/Depth/Segmentation maps of images. The code for collecting image conditions is provided in `annotate_data.py`. 
-
-### Training
-
-Training a Prompt Diffusion is as easy as follows, 
-
-```.bash
-python tool_add_control.py 'path to your stable diffusion checkpoint, e.g., /.../v1-5-pruned-emaonly.ckpt' ./models/control_sd15_ini.ckpt
-
-python train.py --name 'experiment name' --gpus=8 --num_nodes=1 \
-       --logdir 'your logdir path' \
-       --data_config './models/dataset.yaml' --base './models/cldm_v15.yaml' \
-       --sd_locked
-```
-
-We also provide the job script in `scripts/train_v1-5.sh` for an easy run. 
-
-## Run Prompt Diffusion from our checkpoints
-
-We will update the code for playing Prompt Diffusion and the model checkpoints soon. 
-
-## More Examples
-
-![Illustration](./assets/more_example_depth.png)
-![Illustration](./assets/more_example_hed.png)
-![Illustration](./assets/more_example_seg.png)
+## Note
+We have made our pretrained model checkpoints available here. For more information on how to use them, please visit our GitHub page at https://github.com/Zhendong-Wang/Prompt-Diffusion. 
 
 
 ## Citation