File size: 4,060 Bytes
3210048 75bbc61 3210048 78002e6 3210048 9d12334 78002e6 9d12334 3cfa4cc 3210048 3cfa4cc 9d12334 3210048 099273d 3210048 099273d 3210048 78002e6 485f254 3210048 378d4e8 3210048 378d4e8 7ddec05 378d4e8 3210048 78002e6 3210048 78002e6 3210048 78002e6 3210048 78002e6 |
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 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 |
import gradio as gr
import os
from PIL import Image
import torch
from diffusers.utils import load_image, check_min_version
from controlnet_flux import FluxControlNetModel
from transformer_flux import FluxTransformer2DModel
from pipeline_flux_controlnet_inpaint import FluxControlNetInpaintingPipeline
import spaces
import huggingface_hub
huggingface_hub.login(os.getenv('HF_TOKEN_FLUX'))
check_min_version("0.30.2")
transformer = FluxTransformer2DModel.from_pretrained(
"black-forest-labs/FLUX.1-dev", subfolder='transformer', torch_dytpe=torch.bfloat16
)
# Build pipeline
controlnet = FluxControlNetModel.from_pretrained("alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Beta", torch_dtype=torch.bfloat16)
pipe = FluxControlNetInpaintingPipeline.from_pretrained(
"black-forest-labs/FLUX.1-dev",
controlnet=controlnet,
transformer=transformer,
torch_dtype=torch.bfloat16
).to("cuda")
pipe.transformer.to(torch.bfloat16)
pipe.controlnet.to(torch.bfloat16)
MARKDOWN = """
# FLUX.1-dev-Inpainting-Model-Beta-GPU 🔥
Model by alimama-creative
"""
@spaces.GPU()
def process(input_image_editor,
prompt,
negative_prompt,
controlnet_conditioning_scale,
guidance_scale,
seed,
num_inference_steps,
true_guidance_scale
):
image = input_image_editor['background']
mask = input_image_editor['layers'][0]
size = (768, 768)
image_or = image.copy()
image = image.convert("RGB").resize(size)
mask = mask.convert("RGB").resize(size)
generator = torch.Generator(device="cuda").manual_seed(seed)
result = pipe(
prompt=prompt,
height=size[1],
width=size[0],
control_image=image,
control_mask=mask,
num_inference_steps=num_inference_steps,
generator=generator,
controlnet_conditioning_scale=controlnet_conditioning_scale,
guidance_scale=guidance_scale,
negative_prompt=negative_prompt,
true_guidance_scale=true_guidance_scale
).images[0]
return result.resize((image_or.size[:2]))
with gr.Blocks(css=".gradio-container {background-color: #d1d5db;}") as demo:
gr.Markdown(MARKDOWN)
with gr.Row():
with gr.Column():
input_image_editor_component = gr.ImageEditor(
label='Image',
type='pil',
sources=["upload", "webcam"],
image_mode='RGB',
layers=False,
brush=gr.Brush(colors=["#FFFFFF"], color_mode="fixed"))
prompt = gr.Textbox(lines=2, placeholder="Enter prompt here...")
negative_prompt = gr.Textbox(lines=2, placeholder="Enter negative_prompt here...")
controlnet_conditioning_scale = gr.Slider(minimum=0, step=0.01, maximum=1, value=0.9, label="controlnet_conditioning_scale")
guidance_scale = gr.Slider(minimum=1, step=0.5, maximum=10, value=3.5, label="Image to generate")
seed = gr.Slider(minimum=0, step=1, maximum=10000000, value=124, label="Seed Value")
num_inference_steps = gr.Slider(minimum=1, step=1, maximum=30, value=24, label="num_inference_steps")
true_guidance_scale = gr.Slider(minimum=1, step=1, maximum=10, value=3.5, label="true_guidance_scale")
submit_button_component = gr.Button(
value='Submit', variant='primary', scale=0)
with gr.Column():
output_image_component = gr.Image(
type='pil', image_mode='RGB', label='Generated image', format="png")
submit_button_component.click(
fn=process,
inputs=[
input_image_editor_component,
prompt,
negative_prompt,
controlnet_conditioning_scale,
guidance_scale,
seed,
num_inference_steps,
true_guidance_scale
],
outputs=[
output_image_component,
]
)
demo.launch(debug=False, show_error=True,share=True) |