Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Lora doesn't work with fp8 version FLUX! #157

Open
1499544 opened this issue Sep 22, 2024 · 0 comments
Open

Lora doesn't work with fp8 version FLUX! #157

1499544 opened this issue Sep 22, 2024 · 0 comments

Comments

@1499544
Copy link

1499544 commented Sep 22, 2024

hi,i tried fp8 version flux on diffusers,it is amazing. However, it seems that the lora doesn't work. With or without lora, fp8 version output the same pictures. Here's my code, can someone help me?

import torch
from diffusers import DiffusionPipeline, FluxTransformer2DModel
from optimum.quanto import freeze, qfloat8, quantize

device = "cuda" if torch.cuda.is_available() else "cpu"

transformer = FluxTransformer2DModel.from_single_file("https://huggingface.co/Kijai/flux-fp8/blob/main/flux1-dev-fp8.safetensors", torch_dtype=torch.bfloat16)
quantize(transformer, weights=qfloat8)
freeze(transformer)

pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)
pipe.transformer = transformer
pipe = pipe.to(device)

prompt = "A blue jay standing on a large basket of rainbow macarons, disney style"
#prompt = "The portrait of a brazilian person"

generator = torch.Generator(device="cpu").manual_seed(42)
image = pipe(prompt, generator=generator, guidance_scale=3.5).images[0]
image.save("no_lora.png")

pipe.load_lora_weights("XLabs-AI/flux-lora-collection", weight_name="disney_lora.safetensors")
#pipe.load_lora_weights("XLabs-AI/flux-RealismLora")

generator = torch.Generator(device="cpu").manual_seed(42)
image = pipe(prompt, generator=generator, joint_attention_kwargs={"scale": 1}, guidance_scale=3.5).images[0]
image.save("lora_1_0.png")

generator = torch.Generator(device="cpu").manual_seed(42)
image = pipe(prompt, generator=generator, joint_attention_kwargs={"scale": 1.75}, guidance_scale=3.5).images[0]
image.save("lora_1_75.png")

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant