File size: 1,690 Bytes
feb33a0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 |
import torch
from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig, ControlNetInput
import numpy as np
from PIL import Image
pipe = FluxImagePipeline.from_pretrained(
torch_dtype=torch.bfloat16,
device="cuda",
model_configs=[
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors", offload_device="cpu", offload_dtype=torch.float8_e4m3fn),
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors", offload_device="cpu", offload_dtype=torch.float8_e4m3fn),
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/", offload_device="cpu", offload_dtype=torch.float8_e4m3fn),
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors", offload_device="cpu", offload_dtype=torch.float8_e4m3fn),
ModelConfig(model_id="alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Beta", origin_file_pattern="diffusion_pytorch_model.safetensors", offload_device="cpu", offload_dtype=torch.float8_e4m3fn),
],
)
pipe.enable_vram_management()
image_1 = pipe(
prompt="a cat sitting on a chair",
height=1024, width=1024,
seed=8, rand_device="cuda",
)
image_1.save("image_1.jpg")
mask = np.zeros((1024, 1024, 3), dtype=np.uint8)
mask[100:350, 350: -300] = 255
mask = Image.fromarray(mask)
mask.save("mask.jpg")
image_2 = pipe(
prompt="a cat sitting on a chair, wearing sunglasses",
controlnet_inputs=[ControlNetInput(image=image_1, inpaint_mask=mask, scale=0.9)],
height=1024, width=1024,
seed=9, rand_device="cuda",
)
image_2.save("image_2.jpg") |