# pip install diffusers, transformers, accelerate, safetensors, huggingface_hub import os os.system("pip install -U peft") import random import gradio as gr import numpy as np import PIL.Image import spaces import torch from diffusers import AutoPipelineForText2Image, DPMSolverMultistepScheduler from huggingface_hub import hf_hub_download DESCRIPTION = """ # Res-Adapter **Demo by [ameer azam] - [Twitter](https://twitter.com/Ameerazam18) - [GitHub](https://github.com/AMEERAZAM08)) - [Hugging Face](https://huggingface.co/ameerazam08)** This is a demo of https://huggingface.co/jiaxiangc/res-adapter LORAs by ByteDance """ if not torch.cuda.is_available(): DESCRIPTION += "\n

Running on CPU 🥶 This demo does not work on CPU. instead

" MAX_SEED = np.iinfo(np.int32).max CACHE_EXAMPLES = torch.cuda.is_available() and os.getenv("CACHE_EXAMPLES", "0") == "1" MAX_IMAGE_SIZE = int(os.getenv("MAX_IMAGE_SIZE", "1024")) USE_TORCH_COMPILE = os.getenv("USE_TORCH_COMPILE") == "1" ENABLE_CPU_OFFLOAD = os.getenv("ENABLE_CPU_OFFLOAD") == "1" device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") if torch.cuda.is_available(): pipe = AutoPipelineForText2Image.from_pretrained('Lykon/dreamshaper-xl-1-0', torch_dtype=torch.float16, variant="fp16") pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config, use_karras_sigmas=True, algorithm_type="sde-dpmsolver++") pipe = pipe.to("cuda") pipe.load_lora_weights( hf_hub_download( repo_id="jiaxiangc/res-adapter", subfolder="sdxl-i", filename="resolution_lora.safetensors", ), adapter_name="res_adapter", ) pipe.set_adapters(["res_adapter"], adapter_weights=[1.0]) def randomize_seed_fn(seed: int, randomize_seed: bool) -> int: if randomize_seed: seed = random.randint(0, MAX_SEED) return seed @spaces.GPU(enable_queue=True) def generate( prompt: str, negative_prompt: str = "", prompt_2: str = "", negative_prompt_2: str = "", use_negative_prompt: bool = False, use_prompt_2: bool = False, use_negative_prompt_2: bool = False, seed: int = 0, width: int = 1024, height: int = 1024, guidance_scale_base: float = 5.0, num_inference_steps_base: int = 20, progress=gr.Progress(track_tqdm=True), ) -> PIL.Image.Image: print(f"** Generating image for: \"{prompt}\" **") generator = torch.Generator().manual_seed(seed) if not use_negative_prompt: negative_prompt = None # type: ignore if not use_prompt_2: prompt_2 = None # type: ignore if not use_negative_prompt_2: negative_prompt_2 = None # type: ignore base_image = pipe( prompt=prompt, negative_prompt=negative_prompt, prompt_2=prompt_2, negative_prompt_2=negative_prompt_2, width=width, height=height, guidance_scale=guidance_scale_base, num_inference_steps=num_inference_steps_base, generator=generator, output_type="pil").images[0] res_adapt=pipe( prompt=prompt, negative_prompt=negative_prompt, prompt_2=prompt_2, negative_prompt_2=negative_prompt_2, width=width, height=height, guidance_scale=guidance_scale_base, num_inference_steps=num_inference_steps_base, generator=generator, output_type="pil", ).images[0] return [base_image,res_adapt] examples = [ "A realistic photograph of an astronaut in a jungle, cold color palette, detailed, 8k", "An astronaut riding a green horse", ] theme = gr.themes.Base( font=[gr.themes.GoogleFont('Libre Franklin'), gr.themes.GoogleFont('Public Sans'), 'system-ui', 'sans-serif'], ) with gr.Blocks(css="footer{display:none !important}", theme=theme) as demo: gr.Markdown(DESCRIPTION) gr.DuplicateButton( value="Duplicate Space for private use", elem_id="duplicate-button", visible=os.getenv("SHOW_DUPLICATE_BUTTON") == "1", ) with gr.Group(): prompt = gr.Text( label="Prompt", show_label=False, max_lines=1, container=False, placeholder="Enter your prompt", ) run_button = gr.Button("Generate") # result = gr.Gallery(label="Left is Base and Right is Lora"), with gr.Accordion("Advanced options", open=False): with gr.Row(): use_negative_prompt = gr.Checkbox(label="Use negative prompt", value=False) use_prompt_2 = gr.Checkbox(label="Use prompt 2", value=False) use_negative_prompt_2 = gr.Checkbox(label="Use negative prompt 2", value=False) negative_prompt = gr.Text( label="Negative prompt", max_lines=1, placeholder="Enter a negative prompt", visible=False, ) prompt_2 = gr.Text( label="Prompt 2", max_lines=1, placeholder="Enter your prompt", visible=False, ) negative_prompt_2 = gr.Text( label="Negative prompt 2", max_lines=1, placeholder="Enter a negative prompt", visible=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_base = gr.Slider( label="Guidance scale for base", minimum=1, maximum=20, step=0.1, value=7.5, ) num_inference_steps_base = gr.Slider( label="Number of inference steps for base", minimum=10, maximum=100, step=1, value=20, ) gr.Examples( examples=examples, inputs=prompt, outputs=None, fn=generate, cache_examples=CACHE_EXAMPLES, ) use_negative_prompt.change( fn=lambda x: gr.update(visible=x), inputs=use_negative_prompt, outputs=negative_prompt, queue=False, api_name=False, ) use_prompt_2.change( fn=lambda x: gr.update(visible=x), inputs=use_prompt_2, outputs=prompt_2, queue=False, api_name=False, ) use_negative_prompt_2.change( fn=lambda x: gr.update(visible=x), inputs=use_negative_prompt_2, outputs=negative_prompt_2, queue=False, api_name=False, ) gr.on( triggers=[ prompt.submit, negative_prompt.submit, prompt_2.submit, negative_prompt_2.submit, run_button.click, ], fn=randomize_seed_fn, inputs=[seed, randomize_seed], outputs=seed, queue=False, api_name=False, ).then( fn=generate, inputs=[ prompt, negative_prompt, prompt_2, negative_prompt_2, use_negative_prompt, use_prompt_2, use_negative_prompt_2, seed, width, height, guidance_scale_base, num_inference_steps_base, ], outputs=gr.Gallery(label="Left is Base and Right is Lora"), api_name="run", ) if __name__ == "__main__": demo.queue(max_size=20, api_open=False).launch(show_api=False)