Update README.md
Browse files
README.md
CHANGED
@@ -9,7 +9,7 @@ This is an unconditioned 256x256x3 guided-diffusion checkpoint trained with 4.8M
|
|
9 |
|
10 |
#### Sampling
|
11 |
|
12 |
-
Run image_sample.py from OpenAI's guided-diffusion repo or plug it into Disco Diffusion if you wish to
|
13 |
|
14 |
```
|
15 |
python3 scripts/image_sample.py --num_samples 128 --timestep_respacing ddim250 --model_path ema_0.9999_940000.pt --attention_resolutions 32,16,8 --class_cond False --diffusion_steps 1000 --image_size 256 --learn_sigma True --noise_schedule linear --num_channels 256 --num_head_channels 64 --num_res_blocks 2 --resblock_updown True --use_fp16 True --use_scale_shift_norm True --use_ddim True
|
|
|
9 |
|
10 |
#### Sampling
|
11 |
|
12 |
+
Run image_sample.py from OpenAI's guided-diffusion repo or plug it into Disco Diffusion if you wish to diffuse with CLIP guidance.
|
13 |
|
14 |
```
|
15 |
python3 scripts/image_sample.py --num_samples 128 --timestep_respacing ddim250 --model_path ema_0.9999_940000.pt --attention_resolutions 32,16,8 --class_cond False --diffusion_steps 1000 --image_size 256 --learn_sigma True --noise_schedule linear --num_channels 256 --num_head_channels 64 --num_res_blocks 2 --resblock_updown True --use_fp16 True --use_scale_shift_norm True --use_ddim True
|