diffusers
diffusers copied to clipboard
[wip] Higgs quantization
What does this PR do?
Testing code:
from diffusers import DiffusionPipeline, AutoModel
from diffusers.quantizers.quantization_config import HiggsConfig
import torch
ckpt_id = "black-forest-labs/FLUX.1-dev"
transformer = AutoModel.from_pretrained(
ckpt_id,
subfolder="transformer",
quantization_config=HiggsConfig(modules_to_not_convert=["x_embedder"]),
torch_dtype=torch.bfloat16,
device_map="cuda"
)
pipe = DiffusionPipeline.from_pretrained(
ckpt_id,
transformer=transformer,
torch_dtype=torch.bfloat16
).to("cuda")
pipe_kwargs = {
"prompt": "A cat holding a sign that says hello world",
"height": 1024,
"width": 1024,
"guidance_scale": 3.5,
"num_inference_steps": 28,
"max_sequence_length": 512,
"generator": torch.manual_seed(0),
}
image = pipe(**pipe_kwargs).images[0]
image.save("higgs.png")
Cc: @SunMarc @Mekkcyber
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.
Gently pinging @SunMarc @MekkCyber now that the big OSS release is done.