import gradio as gr import numpy as np import random import spaces import torch from diffusers import FluxPipeline dtype = torch.bfloat16 device = "cuda" if torch.cuda.is_available() else "cpu" pipe = FluxPipeline.from_pretrained("Shakker-Labs/AWPortrait-FL", torch_dtype=torch.bfloat16).to(device) MAX_SEED = np.iinfo(np.int32).max MAX_IMAGE_SIZE = 2048 @spaces.GPU(duration=190) def infer(prompt, seed=42, randomize_seed=False, width=768, height=1024, guidance_scale=3.5, num_inference_steps=24, progress=gr.Progress(track_tqdm=True)): if randomize_seed: seed = random.randint(0, MAX_SEED) generator = torch.Generator().manual_seed(seed) image = pipe( prompt=prompt, width=width, height=height, num_inference_steps=num_inference_steps, generator=generator, guidance_scale=guidance_scale ).images[0] return image, seed examples = [ "close up portrait, Amidst the interplay of light and shadows in a photography studio,a soft spotlight traces the contours of a face,highlighting a figure clad in a sleek black turtleneck...", "a cinematic portrait of an elegant elderly man with a wise expression...", "a dramatic close-up shot of a warrior princess with fierce eyes..." ] 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"""# AWPortrait-FL 12B param flow transformer guidance-distilled from [AWPortrait-FL](https://huggingface.co/Shakker-Labs/AWPortrait-FL) [[non-commercial license](https://huggingface.co/Shakker-Labs/AWPortrait-FL/blob/main/LICENSE.md)] """) 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=768, ) 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=24, ) 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()