import gradio as gr from diffusers import DiffusionPipeline import torch import base64 from io import BytesIO import os import gc from share_btn import community_icon_html, loading_icon_html, share_js # SDXL code: https://github.com/huggingface/diffusers/pull/3859 model_dir = os.getenv("SDXL_MODEL_DIR") access_token = os.getenv("ACCESS_TOKEN") if model_dir: # Use local model model_key_base = os.path.join(model_dir, "stable-diffusion-xl-base-0.9") model_key_refiner = os.path.join(model_dir, "stable-diffusion-xl-refiner-0.9") else: model_key_base = "stabilityai/stable-diffusion-xl-base-0.9" model_key_refiner = "stabilityai/stable-diffusion-xl-refiner-0.9" # Use refiner (enabled by default) enable_refiner = os.getenv("ENABLE_REFINER", "true").lower() == "true" # Output images before the refiner and after the refiner output_images_before_refiner = os.getenv("OUTPUT_IMAGES_BEFORE_REFINER", "false").lower() == "true" # Create public link share = os.getenv("SHARE", "false").lower() == "true" print("Loading model", model_key_base) pipe = DiffusionPipeline.from_pretrained(model_key_base, torch_dtype=torch.float16, use_safetensors=True, variant="fp16", use_auth_token=access_token) pipe.enable_model_cpu_offload() # pipe.to("cuda") # if using torch < 2.0 # pipe.enable_xformers_memory_efficient_attention() # pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True) if enable_refiner: print("Loading model", model_key_refiner) pipe_refiner = DiffusionPipeline.from_pretrained(model_key_refiner, torch_dtype=torch.float16, use_safetensors=True, variant="fp16", use_auth_token=access_token) pipe_refiner.enable_model_cpu_offload() # pipe_refiner.to("cuda") # if using torch < 2.0 # pipe_refiner.enable_xformers_memory_efficient_attention() # pipe_refiner.unet = torch.compile(pipe_refiner.unet, mode="reduce-overhead", fullgraph=True) # NOTE: we do not have word list filtering in this gradio demo is_gpu_busy = False def infer(prompt, negative, scale, samples=4, steps=50, refiner_strength=0.3): prompt, negative = [prompt] * samples, [negative] * samples images = pipe(prompt=prompt, negative_prompt=negative, guidance_scale=scale, num_inference_steps=steps).images gc.collect() torch.cuda.empty_cache() images_b64_list = [] if enable_refiner: if output_images_before_refiner: for image in images: buffered = BytesIO() image.save(buffered, format="JPEG") img_str = base64.b64encode(buffered.getvalue()).decode("utf-8") image_b64 = (f"data:image/jpeg;base64,{img_str}") images_b64_list.append(image_b64) images = pipe_refiner(prompt=prompt, negative_prompt=negative, image=images, num_inference_steps=steps, strength=refiner_strength).images gc.collect() torch.cuda.empty_cache() for image in images: buffered = BytesIO() image.save(buffered, format="JPEG") img_str = base64.b64encode(buffered.getvalue()).decode("utf-8") image_b64 = (f"data:image/jpeg;base64,{img_str}") images_b64_list.append(image_b64) return images_b64_list css = """ .gradio-container { font-family: 'IBM Plex Sans', sans-serif; } .gr-button { color: white; border-color: black; background: black; } input[type='range'] { accent-color: black; } .dark input[type='range'] { accent-color: #dfdfdf; } .container { max-width: 730px; margin: auto; padding-top: 1.5rem; } #gallery { min-height: 22rem; margin-bottom: 15px; margin-left: auto; margin-right: auto; border-bottom-right-radius: .5rem !important; border-bottom-left-radius: .5rem !important; } #gallery>div>.h-full { min-height: 20rem; } .details:hover { text-decoration: underline; } .gr-button { white-space: nowrap; } .gr-button:focus { border-color: rgb(147 197 253 / var(--tw-border-opacity)); outline: none; box-shadow: var(--tw-ring-offset-shadow), var(--tw-ring-shadow), var(--tw-shadow, 0 0 #0000); --tw-border-opacity: 1; --tw-ring-offset-shadow: var(--tw-ring-inset) 0 0 0 var(--tw-ring-offset-width) var(--tw-ring-offset-color); --tw-ring-shadow: var(--tw-ring-inset) 0 0 0 calc(3px var(--tw-ring-offset-width)) var(--tw-ring-color); --tw-ring-color: rgb(191 219 254 / var(--tw-ring-opacity)); --tw-ring-opacity: .5; } #advanced-btn { font-size: .7rem !important; line-height: 19px; margin-top: 12px; margin-bottom: 12px; padding: 2px 8px; border-radius: 14px !important; } #advanced-options { display: none; margin-bottom: 20px; } .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; } .acknowledgments h4{ margin: 1.25em 0 .25em 0; font-weight: bold; font-size: 115%; } .animate-spin { animation: spin 1s linear infinite; } @keyframes spin { from { transform: rotate(0deg); } to { transform: rotate(360deg); } } #share-btn-container { display: flex; padding-left: 0.5rem !important; padding-right: 0.5rem !important; background-color: #000000; justify-content: center; align-items: center; border-radius: 9999px !important; width: 13rem; margin-top: 10px; margin-left: auto; } #share-btn { all: initial; color: #ffffff;font-weight: 600; cursor:pointer; font-family: 'IBM Plex Sans', sans-serif; margin-left: 0.5rem !important; padding-top: 0.25rem !important; padding-bottom: 0.25rem !important;right:0; } #share-btn * { all: unset; } #share-btn-container div:nth-child(-n+2){ width: auto !important; min-height: 0px !important; } #share-btn-container .wrap { display: none !important; } .gr-form{ flex: 1 1 50%; border-top-right-radius: 0; border-bottom-right-radius: 0; } #prompt-container{ gap: 0; } #prompt-text-input, #negative-prompt-text-input{padding: .45rem 0.625rem} #component-16{border-top-width: 1px!important;margin-top: 1em} .image_duplication{position: absolute; width: 100px; left: 50px} """ block = gr.Blocks(css=css) examples = [ [ 'A high tech solarpunk utopia in the Amazon rainforest', 'low quality', 9 ], [ 'A pikachu fine dining with a view to the Eiffel Tower', 'low quality', 9 ], [ 'A mecha robot in a favela in expressionist style', 'low quality, 3d, photorealistic', 9 ], [ 'an insect robot preparing a delicious meal', 'low quality, illustration', 9 ], [ "A small cabin on top of a snowy mountain in the style of Disney, artstation", 'low quality, ugly', 9 ], ] with block: gr.HTML( """
Stable Diffusion XL 0.9 is the latest text-to-image model from StabilityAI.
Access SD v2.1 Space SD v1 Space
For faster generation and API access you can try
DreamStudio Beta.