Spaces:
Running
Running
| from typing import Tuple | |
| from PIL import Image | |
| import torch | |
| import spaces | |
| import gradio as gr | |
| import os | |
| # from diffusers.pipelines.flux.pipeline_flux_controlnet_inpaint import ( | |
| # FluxControlNetInpaintPipeline, | |
| # ) | |
| from diffusers.pipelines.flux.pipeline_flux_inpaint import FluxInpaintPipeline | |
| # from diffusers.models.controlnet_flux import FluxControlNetModel | |
| from controlnet_aux import CannyDetector | |
| # login hf token | |
| HF_TOKEN = os.getenv("HF_TOKEN") | |
| # print(HF_TOKEN) | |
| # from huggingface_hub import login | |
| # | |
| # login() | |
| IMAGE_SIZE = 1024 | |
| dtype = torch.bfloat16 | |
| device = "cuda" if torch.cuda.is_available() else "cpu" | |
| base_model = "black-forest-labs/FLUX.1-dev" | |
| controlnet_model = "YishaoAI/flux-dev-controlnet-canny-kid-clothes" | |
| # controlnet = FluxControlNetModel.from_pretrained(controlnet_model, torch_dtype=dtype) | |
| # pipe = FluxControlNetInpaintPipeline.from_pretrained( | |
| # base_model, controlnet=controlnet, torch_dtype=dtype | |
| # ).to(device) | |
| pipe = FluxInpaintPipeline.from_pretrained(base_model, torch_dtype=dtype).to(device) | |
| pipe.enable_model_cpu_offload() | |
| canny = CannyDetector() | |
| def resize_image_dimensions( | |
| original_resolution_wh: Tuple[int, int], | |
| maximum_dimension: int = IMAGE_SIZE | |
| ) -> Tuple[int, int]: | |
| width, height = original_resolution_wh | |
| # if width <= maximum_dimension and height <= maximum_dimension: | |
| # width = width - (width % 32) | |
| # height = height - (height % 32) | |
| # return width, height | |
| if width > height: | |
| scaling_factor = maximum_dimension / width | |
| else: | |
| scaling_factor = maximum_dimension / height | |
| new_width = int(width * scaling_factor) | |
| new_height = int(height * scaling_factor) | |
| new_width = new_width - (new_width % 32) | |
| new_height = new_height - (new_height % 32) | |
| return new_width, new_height | |
| # def get_system_memory(): | |
| # memory = psutil.virtual_memory() | |
| # memory_percent = memory.percent | |
| # memory_used = memory.used / (1024.0**3) | |
| # memory_total = memory.total / (1024.0**3) | |
| # return { | |
| # "percent": f"{memory_percent}%", | |
| # "used": f"{memory_used:.3f}GB", | |
| # "total": f"{memory_total:.3f}GB", | |
| # } | |
| # | |
| def inpaint( | |
| image, | |
| # mask, | |
| prompt, | |
| strength, | |
| num_inference_steps, | |
| guidance_scale, | |
| controlnet_conditioning_scale, | |
| ): | |
| image = image['background'] | |
| mask = image['layers'][0] | |
| width, height = resize_image_dimensions(original_resolution_wh=image.size) | |
| resized_image = image.resize((width, height), Image.LANCZOS) | |
| resized_mask = mask.resize((width, height), Image.LANCZOS) | |
| image_res = pipe( | |
| prompt, | |
| image=resized_image, | |
| # control_image=canny_image, | |
| # controlnet_conditioning_scale=controlnet_conditioning_scale, | |
| mask_image=resized_mask, | |
| strength=strength, | |
| num_inference_steps=num_inference_steps, | |
| guidance_scale=guidance_scale, | |
| ).images[0] | |
| return image_res | |
| with gr.Blocks() as demo: | |
| # gr.LoginButton() | |
| # with gr.Row(): | |
| # with gr.Column(): | |
| # gr.Textbox(value="Hello Memory") | |
| # with gr.Column(): | |
| # gr.JSON(get_system_memory, every=1) | |
| gr.Interface( | |
| fn=inpaint, | |
| inputs=[ | |
| gr.ImageEditor( | |
| label='Image', | |
| type='pil', | |
| sources=["upload", "webcam"], | |
| image_mode='RGB', | |
| layers=False, | |
| brush=gr.Brush(colors=["#FFFFFF"], color_mode="fixed")), | |
| gr.Image(type="pil", label="Input Image"), | |
| # gr.Image(type="pil", label="Mask Image"), | |
| gr.Textbox(label="Prompt"), | |
| gr.Slider(0, 1, value=0.95, label="Strength"), | |
| gr.Slider(1, 100, value=50, step=1, label="Number of Inference Steps"), | |
| gr.Slider(0, 20, value=5, label="Guidance Scale"), | |
| gr.Slider(0, 1, value=0.5, label="ControlNet Conditioning Scale"), | |
| ], | |
| outputs=gr.Image(type="pil", label="Output Image"), | |
| title="Flux Inpaint AI Model", | |
| description="Upload an image and a mask, then provide a prompt to generate an inpainted image.", | |
| ) | |
| demo.launch() | |
| # import gradio as gr | |
| # import numpy as np | |
| # import random | |
| # # import spaces | |
| # import torch | |
| # from diffusers import DiffusionPipeline, FlowMatchEulerDiscreteScheduler, AutoencoderTiny, AutoencoderKL | |
| # from transformers import CLIPTextModel, CLIPTokenizer,T5EncoderModel, T5TokenizerFast | |
| # # from live_preview_helpers import calculate_shift, retrieve_timesteps, flux_pipe_call_that_returns_an_iterable_of_images | |
| # | |
| # dtype = torch.bfloat16 | |
| # device = "cuda" if torch.cuda.is_available() else "cpu" | |
| # | |
| # taef1 = AutoencoderTiny.from_pretrained("madebyollin/taef1", torch_dtype=dtype).to(device) | |
| # good_vae = AutoencoderKL.from_pretrained("black-forest-labs/FLUX.1-schnell", subfolder="vae", torch_dtype=dtype).to(device) | |
| # pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-schnell", torch_dtype=dtype, vae=taef1).to(device) | |
| # torch.cuda.empty_cache() | |
| # | |
| # MAX_SEED = np.iinfo(np.int32).max | |
| # MAX_IMAGE_SIZE = 2048 | |
| # | |
| # # pipe.flux_pipe_call_that_returns_an_iterable_of_images = flux_pipe_call_that_returns_an_iterable_of_images.__get__(pipe) | |
| # | |
| # # @spaces.GPU(duration=75) | |
| # def infer(prompt, seed=42, randomize_seed=False, width=1024, height=1024, guidance_scale=3.5, num_inference_steps=28, progress=gr.Progress(track_tqdm=True)): | |
| # if randomize_seed: | |
| # seed = random.randint(0, MAX_SEED) | |
| # generator = torch.Generator().manual_seed(seed) | |
| # | |
| # for img in pipe.flux_pipe_call_that_returns_an_iterable_of_images( | |
| # prompt=prompt, | |
| # guidance_scale=guidance_scale, | |
| # num_inference_steps=num_inference_steps, | |
| # width=width, | |
| # height=height, | |
| # generator=generator, | |
| # output_type="pil", | |
| # good_vae=good_vae, | |
| # ): | |
| # yield img, seed | |
| # | |
| # examples = [ | |
| # "a tiny astronaut hatching from an egg on the moon", | |
| # "a cat holding a sign that says hello world", | |
| # "an anime illustration of a wiener schnitzel", | |
| # ] | |
| # | |
| # css=""" | |
| # #col-container { | |
| # margin: 0 auto; | |
| # max-width: 520px; | |
| # } | |
| # """ | |
| # | |
| # with gr.Blocks(css=css) as demo: | |
| # | |
| # with gr.Column(elem_id="col-container"): | |
| # gr.Markdown(f"""# FLUX.1 [dev] | |
| # 12B param rectified flow transformer guidance-distilled from [FLUX.1 [pro]](https://blackforestlabs.ai/) | |
| # [[non-commercial license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md)] [[blog](https://blackforestlabs.ai/announcing-black-forest-labs/)] [[model](https://huggingface.co/black-forest-labs/FLUX.1-dev)] | |
| # """) | |
| # | |
| # with gr.Row(): | |
| # | |
| # prompt = gr.Text( | |
| # label="Prompt", | |
| # show_label=False, | |
| # max_lines=1, | |
| # placeholder="Enter your prompt", | |
| # container=False, | |
| # ) | |
| # | |
| # run_button = gr.Button("Run", scale=0) | |
| # | |
| # result = gr.Image(label="Result", show_label=False) | |
| # | |
| # with gr.Accordion("Advanced Settings", open=False): | |
| # | |
| # seed = gr.Slider( | |
| # label="Seed", | |
| # minimum=0, | |
| # maximum=MAX_SEED, | |
| # step=1, | |
| # value=0, | |
| # ) | |
| # | |
| # randomize_seed = gr.Checkbox(label="Randomize seed", value=True) | |
| # | |
| # with gr.Row(): | |
| # | |
| # width = gr.Slider( | |
| # label="Width", | |
| # minimum=256, | |
| # maximum=MAX_IMAGE_SIZE, | |
| # step=32, | |
| # value=1024, | |
| # ) | |
| # | |
| # height = gr.Slider( | |
| # label="Height", | |
| # minimum=256, | |
| # maximum=MAX_IMAGE_SIZE, | |
| # step=32, | |
| # value=1024, | |
| # ) | |
| # | |
| # with gr.Row(): | |
| # | |
| # guidance_scale = gr.Slider( | |
| # label="Guidance Scale", | |
| # minimum=1, | |
| # maximum=15, | |
| # step=0.1, | |
| # value=3.5, | |
| # ) | |
| # | |
| # num_inference_steps = gr.Slider( | |
| # label="Number of inference steps", | |
| # minimum=1, | |
| # maximum=50, | |
| # step=1, | |
| # value=28, | |
| # ) | |
| # | |
| # gr.Examples( | |
| # examples = examples, | |
| # fn = infer, | |
| # inputs = [prompt], | |
| # outputs = [result, seed], | |
| # cache_examples="lazy" | |
| # ) | |
| # | |
| # gr.on( | |
| # triggers=[run_button.click, prompt.submit], | |
| # fn = infer, | |
| # inputs = [prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps], | |
| # outputs = [result, seed] | |
| # ) | |
| # | |
| # demo.launch() | |