Running on CPU š„¶ This demo does not work on CPU. Please use the online demo 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" ENABLE_REFINER = os.getenv("ENABLE_REFINER", "0") == "1" # Global variables for metadata and likes cache image_metadata = pd.DataFrame(columns=['Filename', 'Prompt', 'Likes', 'Dislikes', 'Hearts', 'Created']) LIKES_CACHE_FILE = "likes_cache.json" def load_likes_cache(): if os.path.exists(LIKES_CACHE_FILE): with open(LIKES_CACHE_FILE, 'r') as f: return json.load(f) return {} def save_likes_cache(cache): with open(LIKES_CACHE_FILE, 'w') as f: json.dump(cache, f) likes_cache = load_likes_cache() device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") if torch.cuda.is_available(): vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16) pipe = DiffusionPipeline.from_pretrained("dataautogpt3/OpenDalleV1.1", vae=vae, torch_dtype=torch.float16, use_safetensors=True, variant="fp16") if ENABLE_REFINER: refiner = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-refiner-1.0", vae=vae, torch_dtype=torch.float16, use_safetensors=True, variant="fp16") if ENABLE_CPU_OFFLOAD: pipe.enable_model_cpu_offload() if ENABLE_REFINER: refiner.enable_model_cpu_offload() else: pipe.to(device) if ENABLE_REFINER: refiner.to(device) if USE_TORCH_COMPILE: pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True) if ENABLE_REFINER: refiner.unet = torch.compile(refiner.unet, mode="reduce-overhead", fullgraph=True) def randomize_seed_fn(seed: int, randomize_seed: bool) -> int: return random.randint(0, MAX_SEED) if randomize_seed else seed def create_download_link(filename): with open(filename, "rb") as file: encoded_string = base64.b64encode(file.read()).decode('utf-8') download_link = f'Download Image' return download_link def save_image(image: PIL.Image.Image, prompt: str) -> str: global image_metadata, likes_cache timestamp = datetime.now().strftime("%Y%m%d_%H%M%S") safe_prompt = re.sub(r'[^\w\s-]', '', prompt.lower())[:50] safe_prompt = re.sub(r'[-\s]+', '-', safe_prompt).strip('-') filename = f"{timestamp}_{safe_prompt}.png" image.save(filename) new_row = pd.DataFrame({ 'Filename': [filename], 'Prompt': [prompt], 'Likes': [0], 'Dislikes': [0], 'Hearts': [0], 'Created': [datetime.now()] }) image_metadata = pd.concat([image_metadata, new_row], ignore_index=True) likes_cache[filename] = {'likes': 0, 'dislikes': 0, 'hearts': 0} save_likes_cache(likes_cache) return filename def get_image_gallery(): global image_metadata image_files = image_metadata['Filename'].tolist() return [(file, get_image_caption(file)) for file in image_files if os.path.exists(file)] def get_image_caption(filename): global likes_cache, image_metadata if filename in likes_cache: likes = likes_cache[filename]['likes'] dislikes = likes_cache[filename]['dislikes'] hearts = likes_cache[filename]['hearts'] prompt = image_metadata[image_metadata['Filename'] == filename]['Prompt'].values[0] return f"{filename}\nPrompt: {prompt}\nš {likes} š {dislikes} ā¤ļø {hearts}" return filename def delete_all_images(): global image_metadata, likes_cache for file in image_metadata['Filename']: if os.path.exists(file): os.remove(file) image_metadata = pd.DataFrame(columns=['Filename', 'Prompt', 'Likes', 'Dislikes', 'Hearts', 'Created']) likes_cache = {} save_likes_cache(likes_cache) return get_image_gallery(), image_metadata.values.tolist() def delete_image(filename): global image_metadata, likes_cache if filename and os.path.exists(filename): os.remove(filename) image_metadata = image_metadata[image_metadata['Filename'] != filename] if filename in likes_cache: del likes_cache[filename] save_likes_cache(likes_cache) return get_image_gallery(), image_metadata.values.tolist() def vote(filename, vote_type): global likes_cache if filename in likes_cache: likes_cache[filename][vote_type.lower()] += 1 save_likes_cache(likes_cache) return get_image_gallery(), image_metadata.values.tolist() @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, guidance_scale_refiner: float = 5.0, num_inference_steps_base: int = 25, num_inference_steps_refiner: int = 25, apply_refiner: bool = False, 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 if not use_prompt_2: prompt_2 = None if not use_negative_prompt_2: negative_prompt_2 = None if not apply_refiner: 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] else: latents = 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="latent").images image = refiner(prompt=prompt, negative_prompt=negative_prompt, prompt_2=prompt_2, negative_prompt_2=negative_prompt_2, guidance_scale=guidance_scale_refiner, num_inference_steps=num_inference_steps_refiner, image=latents, generator=generator).images[0] filename = save_image(image, prompt) download_link = create_download_link(filename) return image, get_image_gallery(), download_link, image_metadata.values.tolist() examples = [ f"{random.choice(['Impressionist', 'Cubist', 'Surrealist', 'Abstract Expressionist', 'Pop Art', 'Minimalist', 'Baroque', 'Art Nouveau', 'Pointillist', 'Fauvism'])} painting of a majestic lighthouse on a rocky coast. Use bold brushstrokes and a vibrant color palette to capture the interplay of light and shadow as the lighthouse beam cuts through a stormy night sky.", f"{random.choice(['Impressionist', 'Cubist', 'Surrealist', 'Abstract Expressionist', 'Pop Art', 'Minimalist', 'Baroque', 'Art Nouveau', 'Pointillist', 'Fauvism'])} still life featuring a pair of vintage eyeglasses. Focus on the intricate details of the frames and lenses, using a warm color scheme to evoke a sense of nostalgia and wisdom.", f"{random.choice(['Impressionist', 'Cubist', 'Surrealist', 'Abstract Expressionist', 'Pop Art', 'Minimalist', 'Baroque', 'Art Nouveau', 'Pointillist', 'Fauvism'])} depiction of a rustic wooden stool in a sunlit artist's studio. Emphasize the texture of the wood and the interplay of light and shadow, using a mix of earthy tones and highlights.", f"{random.choice(['Impressionist', 'Cubist', 'Surrealist', 'Abstract Expressionist', 'Pop Art', 'Minimalist', 'Baroque', 'Art Nouveau', 'Pointillist', 'Fauvism'])} scene viewed through an ornate window frame. Contrast the intricate details of the window with a dreamy, soft-focus landscape beyond, using a palette that transitions from cool interior tones to warm exterior hues.", f"{random.choice(['Impressionist', 'Cubist', 'Surrealist', 'Abstract Expressionist', 'Pop Art', 'Minimalist', 'Baroque', 'Art Nouveau', 'Pointillist', 'Fauvism'])} close-up study of interlaced fingers. Use a monochromatic color scheme to emphasize the form and texture of the hands, with dramatic lighting to create depth and emotion.", f"{random.choice(['Impressionist', 'Cubist', 'Surrealist', 'Abstract Expressionist', 'Pop Art', 'Minimalist', 'Baroque', 'Art Nouveau', 'Pointillist', 'Fauvism'])} composition featuring a set of dice in motion. Capture the energy and randomness of the throw, using a dynamic color palette and blurred lines to convey movement.", f"{random.choice(['Impressionist', 'Cubist', 'Surrealist', 'Abstract Expressionist', 'Pop Art', 'Minimalist', 'Baroque', 'Art Nouveau', 'Pointillist', 'Fauvism'])} interpretation of heaven. Create an ethereal atmosphere with soft, billowing clouds and radiant light, using a palette of celestial blues, golds, and whites.", f"{random.choice(['Impressionist', 'Cubist', 'Surrealist', 'Abstract Expressionist', 'Pop Art', 'Minimalist', 'Baroque', 'Art Nouveau', 'Pointillist', 'Fauvism'])} portrayal of an ancient, mystical gate. Combine architectural details with elements of fantasy, using a rich, jewel-toned palette to create an air of mystery and magic.", f"{random.choice(['Impressionist', 'Cubist', 'Surrealist', 'Abstract Expressionist', 'Pop Art', 'Minimalist', 'Baroque', 'Art Nouveau', 'Pointillist', 'Fauvism'])} portrait of a curious cat. Focus on capturing the feline's expressive eyes and sleek form, using a mix of bold and subtle colors to bring out the cat's personality.", f"{random.choice(['Impressionist', 'Cubist', 'Surrealist', 'Abstract Expressionist', 'Pop Art', 'Minimalist', 'Baroque', 'Art Nouveau', 'Pointillist', 'Fauvism'])} abstract representation of toes in sand. Use textured brushstrokes to convey the feeling of warm sand, with a palette inspired by a sun-drenched beach." ] css = ''' .gradio-container {max-width: 1024px !important} h1 {text-align: center} footer {visibility: hidden} ''' theme = gr.themes.Soft() with gr.Blocks(css=css, 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.Tab("Generate Images"): with gr.Group(): with gr.Row(): prompt = gr.Text(label="Prompt", show_label=False, max_lines=1, placeholder="Enter your prompt", container=False) run_button = gr.Button("Generate", scale=0) result = gr.Image(label="Result", show_label=False) download_link = gr.HTML(label="Download", show_label=False) with gr.Accordion("Advanced options", open=False): 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 second prompt", visible=False) negative_prompt_2 = gr.Text(label="Negative prompt 2", max_lines=1, placeholder="Enter a second 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) apply_refiner = gr.Checkbox(label="Apply refiner", value=False, visible=ENABLE_REFINER) with gr.Row(): guidance_scale_base = gr.Slider(label="Guidance scale for base", minimum=1, maximum=20, step=0.1, value=5.0) num_inference_steps_base = gr.Slider(label="Number of inference steps for base", minimum=10, maximum=100, step=1, value=25) with gr.Row(visible=False) as refiner_params: guidance_scale_refiner = gr.Slider(label="Guidance scale for refiner", minimum=1, maximum=20, step=0.1, value=5.0) num_inference_steps_refiner = gr.Slider(label="Number of inference steps for refiner", minimum=10, maximum=100, step=1, value=25) with gr.Tab("Gallery and Voting"): image_gallery = gr.Gallery(label="Generated Images", show_label=True, columns=4, height="auto") with gr.Row(): like_button = gr.Button("š Like") dislike_button = gr.Button("š Dislike") heart_button = gr.Button("ā¤ļø Heart") delete_image_button = gr.Button("šļø Delete Selected Image") selected_image = gr.State(None) with gr.Tab("Metadata and Management"): metadata_df = gr.Dataframe( label="Image Metadata", headers=["Filename", "Prompt", "Likes", "Dislikes", "Hearts", "Created"], interactive=False ) delete_all_button = gr.Button("šļø Delete All Images") gr.Examples(examples=examples, inputs=prompt, outputs=[result, image_gallery, download_link, metadata_df], 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) apply_refiner.change(fn=lambda x: gr.update(visible=x), inputs=apply_refiner, outputs=refiner_params, queue=False, api_name=False) prompt.submit(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, guidance_scale_refiner, num_inference_steps_base, num_inference_steps_refiner, apply_refiner], outputs=[result, image_gallery, download_link, metadata_df] ) 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, guidance_scale_refiner, num_inference_steps_base, num_inference_steps_refiner, apply_refiner], outputs=[result, image_gallery, download_link, metadata_df] ) image_gallery.select(fn=lambda evt: evt, inputs=[], outputs=[selected_image]) like_button.click(fn=lambda x: vote(x, 'likes'), inputs=[selected_image], outputs=[image_gallery, metadata_df]) dislike_button.click(fn=lambda x: vote(x, 'dislikes'), inputs=[selected_image], outputs=[image_gallery, metadata_df]) heart_button.click(fn=lambda x: vote(x, 'hearts'), inputs=[selected_image], outputs=[image_gallery, metadata_df]) delete_image_button.click(fn=delete_image, inputs=[selected_image], outputs=[image_gallery, metadata_df]) delete_all_button.click(fn=delete_all_images, inputs=[], outputs=[image_gallery, metadata_df]) demo.load(fn=lambda: (get_image_gallery(), image_metadata.values.tolist()), outputs=[image_gallery, metadata_df]) if __name__ == "__main__": demo.queue(max_size=20).launch(share=True, debug=False)