import gradio as gr import numpy as np import random from peft import PeftModel, LoraConfig # import spaces #[uncomment to use ZeroGPU] from diffusers import DiffusionPipeline import torch device = "cuda" if torch.cuda.is_available() else "cpu" if torch.cuda.is_available(): torch_dtype = torch.float16 else: torch_dtype = torch.float32 MAX_SEED = np.iinfo(np.int32).max MAX_IMAGE_SIZE = 1024 # @spaces.GPU #[uncomment to use ZeroGPU] def infer( model_id, prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps, lscale, controlnet_enabled, control_strength, control_mode, control_image, ip_adapter_enabled, ip_adapter_scale, ip_adapter_image, progress=gr.Progress(track_tqdm=True), ): if randomize_seed: seed = random.randint(0, MAX_SEED) generator = torch.Generator().manual_seed(seed) pipe = None if (model_id=="stable-diffusion-v1-5/stable-diffusion-v1-5 with lora"): pipe=DiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch_dtype) pipe.unet = PeftModel.from_pretrained(pipe.unet,"um235/cartoon_cat_stickers/unet") pipe.text_encoder= PeftModel.from_pretrained(pipe.text_encoder,"um235/cartoon_cat_stickers/text_encoder") else: print("stable-diffusion-v1-5/stable-diffusion-v1-5 with lora") pipe=DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch_dtype) pipe = pipe.to(device) image = pipe( prompt=prompt, negative_prompt=negative_prompt, guidance_scale=guidance_scale, num_inference_steps=num_inference_steps, width=width, height=height, generator=generator, cross_attention_kwargs={"scale": lscale} ).images[0] return image, seed examples = [ "Sticker VanillaCat. Cartoon-style cat with soft yellow fur and a white flower on its head, sitting up with a relaxed expression, eyes half-closed, content and calm, casual pose, peaceful mood, white background.", "Sticker VanillaCat. Cartoon-style cat with soft yellow fur and a white flower on its head, standing with a mischievous grin, one paw raised playfully, bright eyes full of energy, cheeky and fun, white background", "Sticker VanillaCat. Cartoon-style cat with soft yellow fur and a white flower on its head, jumping mid-air with a surprised expression, wide eyes, and mouth open in excitement, paws stretched out, energetic and playful, forest background.", ] css = """ #col-container { margin: 0 auto; max-width: 640px; } """ def update_controlnet_visibility(controlnet_enabled): # Возвращаем два значения для обновления видимости control_strength и control_mode return gr.update(visible=controlnet_enabled), gr.update(visible=controlnet_enabled), gr.update(visible=controlnet_enabled) def update_ip_adapter_visibility(ip_adapter_enabled): # Возвращаем два значения для обновления видимости ip_adapter_scale и ip_adapter_image return gr.update(visible=ip_adapter_enabled), gr.update(visible=ip_adapter_enabled) with gr.Blocks(css=css) as demo: with gr.Column(elem_id="col-container"): gr.Markdown(" # UM235 DIFFUSION Space") model_id_input = gr.Dropdown( label="Choose Model", choices=[ "stable-diffusion-v1-5/stable-diffusion-v1-5", "CompVis/stable-diffusion-v1-4", "stable-diffusion-v1-5/stable-diffusion-v1-5 with lora", ], value="stable-diffusion-v1-5/stable-diffusion-v1-5 with lora", show_label=True, type="value", ) with gr.Row(): lscale = gr.Slider( label="Lora scale", minimum=0, maximum=2, step=0.05, value=1, ) with gr.Row(): prompt = gr.Text( label="Prompt", show_label=False, max_lines=1, placeholder="Enter your prompt", container=False, ) with gr.Accordion("ControlNet Settings", open=False): controlnet_enabled = gr.Checkbox(label="Enable ControlNet", value=False) with gr.Row(): control_strength = gr.Slider( label="ControlNet scale", minimum=0.0, maximum=1.0, step=0.05, value=0.75, visible=False, ) control_mode = gr.Dropdown( label="ControlNet Mode", choices=["edge_detection", "pose_estimation", "depth_estimation"], value="edge_detection", visible=False, ) control_image = gr.Image(label="ControlNet Image", type="pil", visible=False) with gr.Accordion("IP-Adapter Settings", open=False): ip_adapter_enabled = gr.Checkbox(label="Enable IP-Adapter", value=False) with gr.Row(): ip_adapter_scale = gr.Slider( label="IP-Adapter Scale", minimum=0.0, maximum=2.0, step=0.05, value=1.0, visible=False, ) ip_adapter_image = gr.Image(label="IP-Adapter Image", type="pil", visible=False) with gr.Row(): run_button = gr.Button("Run", scale=0, variant="primary") result = gr.Image(label="Result", show_label=False) with gr.Accordion("Advanced Settings", open=False): negative_prompt = gr.Text( label="Negative prompt", max_lines=1, placeholder="Enter a negative prompt", visible=True, ) seed = gr.Slider( label="Seed", minimum=0, maximum=MAX_SEED, step=1, value=42, ) 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=512, # Replace with defaults that work for your model ) height = gr.Slider( label="Height", minimum=256, maximum=MAX_IMAGE_SIZE, step=32, value=512, # Replace with defaults that work for your model ) with gr.Row(): guidance_scale = gr.Slider( label="Guidance scale", minimum=0.0, maximum=10.0, step=0.1, value=7.0, # Replace with defaults that work for your model ) num_inference_steps = gr.Slider( label="Number of inference steps", minimum=1, maximum=50, step=1, value=20, # Replace with defaults that work for your model ) gr.Examples(examples=examples, inputs=[prompt]) gr.on( triggers=[run_button.click, prompt.submit], fn=infer, inputs=[ model_id_input, prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps, lscale, controlnet_enabled, control_strength, control_mode, control_image, ip_adapter_enabled, ip_adapter_scale, ip_adapter_image, ], outputs=[result, seed], ) controlnet_enabled.change( fn=update_controlnet_visibility, inputs=[controlnet_enabled], outputs=[control_strength, control_mode, control_image], ) # Updates visibility when the checkbox for IP-Adapter is toggled ip_adapter_enabled.change( fn=update_ip_adapter_visibility, inputs=[ip_adapter_enabled], outputs=[ip_adapter_scale, ip_adapter_image], ) if __name__ == "__main__": demo.launch()