AI/diffusers
1
0
Fork 0
mirror of https://github.com/huggingface/diffusers.git synced 2026-01-27 17:22:53 +03:00
Code Activity

[Docs] Advertise fp16 instead of autocast (#740)

Browse Source 
up
This commit is contained in:
Patrick von Platen
2022-10-05 22:20:53 +02:00
committed by GitHub
parent 5493524b71
commit 4deb16e830
9 changed files with 40 additions and 38 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/source/using-diffusers/img2img.mdx
View File

@@ -15,7 +15,6 @@ specific language governing permissions and limitations under the License.
The [`StableDiffusionImg2ImgPipeline`] lets you pass a text prompt and an initial image to condition the generation of new images.
```python
from torch import autocast
import requests
from PIL import Image
from io import BytesIO
@@ -37,8 +36,7 @@ init_image = init_image.resize((768, 512))
prompt = "A fantasy landscape, trending on artstation"
with autocast("cuda"):
images = pipe(prompt=prompt, init_image=init_image, strength=0.75, guidance_scale=7.5).images
images = pipe(prompt=prompt, init_image=init_image, strength=0.75, guidance_scale=7.5).images
images[0].save("fantasy_landscape.png")
```

4
docs/source/using-diffusers/inpaint.mdx
View File

@@ -17,7 +17,6 @@ The [`StableDiffusionInpaintPipeline`] lets you edit specific parts of an image
```python
from io import BytesIO
from torch import autocast
import requests
import PIL
@@ -41,8 +40,7 @@ pipe = StableDiffusionInpaintPipeline.from_pretrained(
).to(device)
prompt = "a cat sitting on a bench"
with autocast("cuda"):
images = pipe(prompt=prompt, init_image=init_image, mask_image=mask_image, strength=0.75).images
images = pipe(prompt=prompt, init_image=init_image, mask_image=mask_image, strength=0.75).images
images[0].save("cat_on_bench.png")
```