import gradio as gr from PIL import Image from io import BytesIO import torch import os from diffusers import DiffusionPipeline, DDIMScheduler MY_SECRET_TOKEN=os.environ.get('HF_TOKEN_SD') has_cuda = torch.cuda.is_available() device = torch.device('cpu' if not has_cuda else 'cuda') pipe = DiffusionPipeline.from_pretrained( "CompVis/stable-diffusion-v1-4", safety_checker=None, use_auth_token=MY_SECRET_TOKEN, custom_pipeline="imagic_stable_diffusion", scheduler = DDIMScheduler(beta_start=0.00085, beta_end=0.012, beta_schedule="scaled_linear", clip_sample=False, set_alpha_to_one=False) ).to(device) #generator = torch.Generator("cuda").manual_seed(0) def infer(prompt, init_image): init_image = Image.open(BytesIO(init_image)).convert("RGB") init_image = init_image.resize((512, 512)) res = pipe.train( prompt, init_image, guidance_scale=7.5, num_inference_steps=50) res = pipe(alpha=1) return res.images[0] title = """

Imagic Stable Diffusion • Community Pipeline

Text-Based Real Image Editing with Diffusion Models
This pipeline aims to implement this paper to Stable Diffusion, allowing for real-world image editing.


You can skip the queue by duplicating this space: Duplicate Space

""" article = """ """ css = ''' #col-container {max-width: 700px; margin-left: auto; margin-right: auto;} a {text-decoration-line: underline; font-weight: 600;} .footer { margin-bottom: 45px; margin-top: 35px; text-align: center; border-bottom: 1px solid #e5e5e5; } .footer>p { font-size: .8rem; display: inline-block; padding: 0 10px; transform: translateY(10px); background: white; } .dark .footer { border-color: #303030; } .dark .footer>p { background: #0b0f19; } ''' with gr.Blocks(css=css) as block: with gr.Column(elem_id="col-container"): gr.HTML(title) prompt_input = gr.Textbox(label="Target text", placeholder="Describe the image with what you want to change about the subject") image_init = gr.Image(source="upload", type="binary",label="Input Image") submit_btn = gr.Button("Submit") image_output = gr.Image(label="Edited image") gr.HTML(article) submit_btn.click(fn=infer, inputs=[prompt_input,image_init], outputs=[image_output]) block.queue(max_size=32,concurrency_count=20).launch(show_api=False)