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
Superresolution code is currently bugged because it does not accept height and width, and rather just assigns a height and width of 256x256. This results in squished images when you try to super resolution anything from the first stage model that is not 64x64.
Solution: Just allow height and width to be passed in. I forked the class and did this manually and it works fine.
Reproduction
fromdiffusersimportDiffusionPipelinefromdiffusers.utilsimportpt_to_pilimporttorch# stage 1stage_1=DiffusionPipeline.from_pretrained("DeepFloyd/IF-I-XL-v1.0", variant="fp16", torch_dtype=torch.float16)
stage_1.enable_model_cpu_offload()
# stage 2stage_2=DiffusionPipeline.from_pretrained(
"DeepFloyd/IF-II-L-v1.0", text_encoder=None, variant="fp16", torch_dtype=torch.float16
)
stage_2.enable_model_cpu_offload()
prompt='a photo of a kangaroo wearing an orange hoodie and blue sunglasses standing in front of the eiffel tower holding a sign that says "very deep learning"'generator=torch.manual_seed(1)
# text embedsprompt_embeds, negative_embeds=stage_1.encode_prompt(prompt)
# stage 1image=stage_1(
prompt_embeds=prompt_embeds,
negative_prompt_embeds=negative_embeds,
generator=generator,
output_type="pt",
height=96,
width=64,
).imagespt_to_pil(image)[0].save("./if_stage_I.png")
# stage 2image=stage_2(
image=image,
prompt_embeds=prompt_embeds,
negative_prompt_embeds=negative_embeds,
generator=generator,
output_type="pt",
).imagespt_to_pil(image)[0].save("./if_stage_II.png")
Logs
No response
System Info
py 3.10.6, diffusers on latest main
The text was updated successfully, but these errors were encountered:
Describe the bug
Superresolution code is currently bugged because it does not accept height and width, and rather just assigns a height and width of 256x256. This results in squished images when you try to super resolution anything from the first stage model that is not 64x64.
diffusers/src/diffusers/pipelines/deepfloyd_if/pipeline_if_superresolution.py
Lines 809 to 810 in eade430
Solution: Just allow height and width to be passed in. I forked the class and did this manually and it works fine.
Reproduction
Logs
No response
System Info
py 3.10.6, diffusers on latest main
The text was updated successfully, but these errors were encountered: