import sentencepiece import torch import spaces import gradio as gr import os from diffusers.pipelines.flux.pipeline_flux_controlnet_inpaint import ( FluxControlNetInpaintPipeline, ) 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() 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.enable_model_cpu_offload() canny = CannyDetector() @spaces.GPU(duration=160) def inpaint( image, mask, prompt, strength, num_inference_steps, guidance_scale, controlnet_conditioning_scale, ): canny_image = canny(image) image_res = pipe( prompt, image=image, control_image=canny_image, controlnet_conditioning_scale=controlnet_conditioning_scale, mask_image=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() gr.Interface( fn=inpaint, inputs=[ 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()