kandinsky-community
/

kandinsky-2-1-prior

KandinskyPriorPipeline

Model card Files Files and versions Community

YiYiXu commited on Jun 9, 2023

Commit

dd3c978

•

1 Parent(s): 40cd431

Update README.md

Files changed (1) hide show

README.md +2 -4

README.md CHANGED Viewed

@@ -34,8 +34,7 @@ t2i_pipe.to("cuda")
 prompt = "A alien cheeseburger creature eating itself, claymation, cinematic, moody lighting"
 negative_prompt = "low quality, bad quality"
-generator = torch.Generator(device="cuda").manual_seed(12)
-image_embeds, negative_image_embeds = pipe_prior(prompt, negative_prompt, generator=generator).to_tuple()
 image = t2i_pipe(prompt, image_embeds=image_embeds, negative_image_embeds=negative_image_embeds).images[0]
 image.save("cheeseburger_monster.png")
@@ -72,8 +71,7 @@ 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()
 out = pipe(
     prompt,

 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).to_tuple()
 image = t2i_pipe(prompt, image_embeds=image_embeds, negative_image_embeds=negative_image_embeds).images[0]
 image.save("cheeseburger_monster.png")
 prompt = "A fantasy landscape, Cinematic lighting"
 negative_prompt = "low quality, bad quality"
+image_embeds, negative_image_embeds = pipe_prior(prompt, negative_prompt).to_tuple()
 out = pipe(
     prompt,