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

remove seed (#3734)

Browse Source 
* remove seed

* style

---------

Co-authored-by: yiyixuxu <yixu310@gmail,com>
This commit is contained in:
YiYi Xu
2023-06-09 08:27:02 -10:00
committed by GitHub
parent c42f6ee43e
commit 05361960f2
1 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
docs/source/en/api/pipelines/kandinsky.mdx
View File

@@ -60,8 +60,7 @@ returns both the image embeddings corresponding to the prompt and negative/uncon
embeddings corresponding to an empty string.
```py
generator = torch.Generator(device="cuda").manual_seed(12)
image_embeds, negative_image_embeds = pipe_prior(prompt, generator=generator).to_tuple()
image_embeds, negative_image_embeds = pipe_prior(prompt, guidance_scale=1.0).to_tuple()
```
<Tip warning={true}>
@@ -78,7 +77,7 @@ of the prior by a factor of 2.
prompt = "A alien cheeseburger creature eating itself, claymation, cinematic, moody lighting"
negative_prompt = "low quality, bad quality"
image_embeds, negative_image_embeds = pipe_prior(prompt, negative_prompt, generator=generator).to_tuple()
image_embeds, negative_image_embeds = pipe_prior(prompt, negative_prompt, guidance_scale=1.0).to_tuple()
```
</Tip>
@@ -89,7 +88,9 @@ in case you are using a customized negative prompt, that you should pass this on
with `negative_prompt=negative_prompt`:
```py
image = t2i_pipe(prompt, image_embeds=image_embeds, negative_image_embeds=negative_image_embeds).images[0]
image = t2i_pipe(
prompt, image_embeds=image_embeds, negative_image_embeds=negative_image_embeds, height=768, width=768
).images[0]
image.save("cheeseburger_monster.png")
```
@@ -160,8 +161,7 @@ pipe.to("cuda")
prompt = "A fantasy landscape, Cinematic lighting"
negative_prompt = "low quality, bad quality"
generator = torch.Generator(device="cuda").manual_seed(30)
image_embeds, negative_image_embeds = pipe_prior(prompt, negative_prompt, generator=generator).to_tuple()
image_embeds, negative_image_embeds = pipe_prior(prompt, negative_prompt).to_tuple()
out = pipe(
prompt,