You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
As shown in the following code, I have set the height and width to 2048 when call the pipeline. However, the output image is still 1024*1024. How can I solve this problem? Thanks.
importtorchfromdiffusersimportPixArtAlphaPipeline# You can replace the checkpoint id with "PixArt-alpha/PixArt-XL-2-512x512" too.pipeline=PixArtAlphaPipeline.from_pretrained("PixArt-alpha/PixArt-XL-2-1024-MS", torch_dtype=torch.float16)
# Enable memory optimizations.pipeline=pipeline.to("cuda")
torch.manual_seed(42)
torch.cuda.manual_seed_all(42)
prompt="alien, glowing eyes, crystal body."image=pipeline(height=2048,width=2048,prompt=prompt,use_resolution_binning=True).images[0]
image.save(f"output.jpg")
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
As shown in the following code, I have set the
height
andwidth
to 2048 when call the pipeline. However, the output image is still 1024*1024. How can I solve this problem? Thanks.Beta Was this translation helpful? Give feedback.
All reactions