GitHub

Original file line numberDiff line numberDiff line change

@@ -70,28 +70,16 @@ We provide a first script for sampling from our unconditional models. Start it v

7070

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>

7171

```

7272
73-

# Inpainting

74-

![inpainting](assets/inpainting.png)

75-
76-

Download the pre-trained weights

77-

```

78-

wget XXX

79-

```

73+

## Coming Soon...

8074
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...

75+

![inpainting](assets/inpainting.png)

9076
9177

* Code for training LDMs and the corresponding compression models.

9278

* Inference scripts for conditional LDMs for various conditioning modalities.

9379

* In the meantime, you can play with our colab notebook https://colab.research.google.com/drive/1xqzUi2iXQXDqXBHQGP9Mqt2YrYW6cx-J?usp=sharing

9480

* We will also release some further pretrained models.

81+
82+
9583

## Comments

9684
9785

- Our codebase for the diffusion models builds heavily on [OpenAI's codebase](https://github.com/openai/guided-diffusion)

Read the original on github.com ↗