ablattmann commited on
Commit
635548d
1 Parent(s): aea2f58

Update README.md

Browse files

Former-commit-id: 17e64e320556d49e429f41a7093b291c49255470

Files changed (1) hide show
  1. README.md +4 -16
README.md CHANGED
@@ -70,28 +70,16 @@ We provide a first script for sampling from our unconditional models. Start it v
70
  CUDA_VISIBLE_DEVICES=<GPU_ID> python scripts/sample_diffusion.py -r models/ldm/<model_spec>/model.ckpt -l <logdir> -n <\#samples> --batch_size <batch_size> -c <\#ddim steps> -e <\#eta>
71
  ```
72
 
73
- # Inpainting
74
- ![inpainting](assets/inpainting.png)
75
-
76
- Download the pre-trained weights
77
- ```
78
- wget XXX
79
- ```
80
 
81
- and sample with
82
- ```
83
- python scripts/inpaint.py --indir data/inpainting_examples/ --outdir outputs/inpainting_results
84
- ```
85
- `indir` should contain images `*.png` and masks `<image_fname>_mask.png` like
86
- the examples provided in `data/inpainting_examples`.
87
-
88
-
89
- ## Comin Soon...
90
 
91
  * Code for training LDMs and the corresponding compression models.
92
  * Inference scripts for conditional LDMs for various conditioning modalities.
93
  * In the meantime, you can play with our colab notebook https://colab.research.google.com/drive/1xqzUi2iXQXDqXBHQGP9Mqt2YrYW6cx-J?usp=sharing
94
  * We will also release some further pretrained models.
 
 
95
  ## Comments
96
 
97
  - Our codebase for the diffusion models builds heavily on [OpenAI's codebase](https://github.com/openai/guided-diffusion)
 
70
  CUDA_VISIBLE_DEVICES=<GPU_ID> python scripts/sample_diffusion.py -r models/ldm/<model_spec>/model.ckpt -l <logdir> -n <\#samples> --batch_size <batch_size> -c <\#ddim steps> -e <\#eta>
71
  ```
72
 
73
+ ## Coming Soon...
 
 
 
 
 
 
74
 
75
+ ![inpainting](assets/inpainting.png)
 
 
 
 
 
 
 
 
76
 
77
  * Code for training LDMs and the corresponding compression models.
78
  * Inference scripts for conditional LDMs for various conditioning modalities.
79
  * In the meantime, you can play with our colab notebook https://colab.research.google.com/drive/1xqzUi2iXQXDqXBHQGP9Mqt2YrYW6cx-J?usp=sharing
80
  * We will also release some further pretrained models.
81
+
82
+
83
  ## Comments
84
 
85
  - Our codebase for the diffusion models builds heavily on [OpenAI's codebase](https://github.com/openai/guided-diffusion)