Spaces:
Running
Running
| #!/usr/bin/env python | |
| from __future__ import annotations | |
| import argparse | |
| import os | |
| import sys | |
| import random | |
| import gradio as gr | |
| import numpy as np | |
| import uuid | |
| import spaces | |
| from diffusers import ConsistencyDecoderVAE, DPMSolverMultistepScheduler, Transformer2DModel, AutoencoderKL | |
| import torch | |
| from typing import Tuple | |
| from datetime import datetime | |
| from peft import PeftModel | |
| from diffusers_patches import pixart_sigma_init_patched_inputs, PixArtSigmaPipeline | |
| DESCRIPTION = """ # Instant Image | |
| ### Super fast text to Image Generator. | |
| ### <span style='color: red;'>You may change the steps from 9 to 15, if you didn't get satisfied results. | |
| """ | |
| if not torch.cuda.is_available(): | |
| DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>" | |
| MAX_SEED = np.iinfo(np.int32).max | |
| CACHE_EXAMPLES = torch.cuda.is_available() and os.getenv("CACHE_EXAMPLES", "1") == "1" | |
| MAX_IMAGE_SIZE = int(os.getenv("MAX_IMAGE_SIZE", "6000")) | |
| USE_TORCH_COMPILE = os.getenv("USE_TORCH_COMPILE", "0") == "1" | |
| ENABLE_CPU_OFFLOAD = os.getenv("ENABLE_CPU_OFFLOAD", "0") == "1" | |
| PORT = int(os.getenv("DEMO_PORT", "15432")) | |
| device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") | |
| style_list = [ | |
| { | |
| "name": "(No style)", | |
| "prompt": "{prompt}", | |
| "negative_prompt": "", | |
| }, | |
| { | |
| "name": "Cinematic", | |
| "prompt": "cinematic still {prompt} . emotional, harmonious, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy", | |
| "negative_prompt": "anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured", | |
| }, | |
| { | |
| "name": "Realistic", | |
| "prompt": "Photorealistic {prompt} . Ulta-realistic, professional, 4k, highly detailed", | |
| "negative_prompt": "drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly, disfigured", | |
| }, | |
| { | |
| "name": "Anime", | |
| "prompt": "anime artwork {prompt} . anime style, key visual, vibrant, studio anime, highly detailed", | |
| "negative_prompt": "photo, deformed, black and white, realism, disfigured, low contrast", | |
| }, | |
| { | |
| "name": "Manga", | |
| "prompt": "manga style {prompt} . vibrant, high-energy, detailed, iconic, Japanese comic style", | |
| "negative_prompt": "ugly, deformed, noisy, blurry, low contrast, realism, photorealistic, Western comic style", | |
| }, | |
| { | |
| "name": "Digital Art", | |
| "prompt": "concept art {prompt} . digital artwork, illustrative, painterly, matte painting, highly detailed", | |
| "negative_prompt": "photo, photorealistic, realism, ugly", | |
| }, | |
| { | |
| "name": "Pixel art", | |
| "prompt": "pixel-art {prompt} . low-res, blocky, pixel art style, 8-bit graphics", | |
| "negative_prompt": "sloppy, messy, blurry, noisy, highly detailed, ultra textured, photo, realistic", | |
| }, | |
| { | |
| "name": "Fantasy art", | |
| "prompt": "ethereal fantasy concept art of {prompt} . magnificent, celestial, ethereal, painterly, epic, majestic, magical, fantasy art, cover art, dreamy", | |
| "negative_prompt": "photographic, realistic, realism, 35mm film, dslr, cropped, frame, text, deformed, glitch, noise, noisy, off-center, deformed, cross-eyed, closed eyes, bad anatomy, ugly, disfigured, sloppy, duplicate, mutated, black and white", | |
| }, | |
| { | |
| "name": "Neonpunk", | |
| "prompt": "neonpunk style {prompt} . cyberpunk, vaporwave, neon, vibes, vibrant, stunningly beautiful, crisp, detailed, sleek, ultramodern, magenta highlights, dark purple shadows, high contrast, cinematic, ultra detailed, intricate, professional", | |
| "negative_prompt": "painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured", | |
| }, | |
| { | |
| "name": "3D Model", | |
| "prompt": "professional 3d model {prompt} . octane render, highly detailed, volumetric, dramatic lighting", | |
| "negative_prompt": "ugly, deformed, noisy, low poly, blurry, painting", | |
| }, | |
| ] | |
| styles = {k["name"]: (k["prompt"], k["negative_prompt"]) for k in style_list} | |
| STYLE_NAMES = list(styles.keys()) | |
| DEFAULT_STYLE_NAME = "(No style)" | |
| " | |
| SCHEDULE_NAME = ["DPM-Solver"] | |
| DEFAULT_SCHEDULE_NAME = "DPM-Solver" | |
| NUM_IMAGES_PER_PROMPT = 1 | |
| def apply_style(style_name: str, positive: str, negative: str = "") -> Tuple[str, str]: | |
| p, n = styles.get(style_name, styles[DEFAULT_STYLE_NAME]) | |
| if not negative: | |
| negative = "" | |
| return p.replace("{prompt}", positive), n + negative | |
| if torch.cuda.is_available(): | |
| weight_dtype = torch.float16 | |
| T5_token_max_length = 300 | |
| # tmp patches for diffusers PixArtSigmaPipeline Implementation | |
| print( | |
| "Changing _init_patched_inputs method of diffusers.models.Transformer2DModel " | |
| "using scripts.diffusers_patches.pixart_sigma_init_patched_inputs") | |
| setattr(Transformer2DModel, '_init_patched_inputs', pixart_sigma_init_patched_inputs) | |
| transformer = Transformer2DModel.from_pretrained( | |
| "PixArt-alpha/PixArt-Sigma-XL-2-1024-MS", | |
| subfolder='transformer', | |
| torch_dtype=weight_dtype, | |
| ) | |
| pipe = PixArtSigmaPipeline.from_pretrained( | |
| "PixArt-alpha/pixart_sigma_sdxlvae_T5_diffusers", | |
| transformer=transformer, | |
| torch_dtype=weight_dtype, | |
| use_safetensors=True, | |
| ) | |
| if os.getenv('CONSISTENCY_DECODER', False): | |
| print("Using DALL-E 3 Consistency Decoder") | |
| pipe.vae = ConsistencyDecoderVAE.from_pretrained("openai/consistency-decoder", torch_dtype=torch.float16) | |
| if ENABLE_CPU_OFFLOAD: | |
| pipe.enable_model_cpu_offload() | |
| else: | |
| pipe.to(device) | |
| print("Loaded on Device!") | |
| # speed-up T5 | |
| pipe.text_encoder.to_bettertransformer() | |
| if USE_TORCH_COMPILE: | |
| pipe.transformer = torch.compile(pipe.transformer, mode="reduce-overhead", fullgraph=True) | |
| print("Model Compiled!") | |
| def save_image(img): | |
| unique_name = str(uuid.uuid4()) + ".png" | |
| img.save(unique_name) | |
| return unique_name | |
| def randomize_seed_fn(seed: int, randomize_seed: bool) -> int: | |
| if randomize_seed: | |
| seed = random.randint(0, MAX_SEED) | |
| return seed | |
| @torch.no_grad() | |
| @torch.inference_mode() | |
| @spaces.GPU(duration=120) | |
| def generate( | |
| prompt: str, | |
| negative_prompt: str = "", | |
| style: str = DEFAULT_STYLE_NAME, | |
| use_negative_prompt: bool = False, | |
| num_imgs: int = 1, | |
| seed: int = 0, | |
| width: int = 400, | |
| height: int = 400, | |
| schedule: str = 'DPM-Solver', | |
| dpms_guidance_scale: float = 3.5, | |
| dpms_inference_steps: int = 9, | |
| randomize_seed: bool = False, | |
| use_resolution_binning: bool = True, | |
| progress=gr.Progress(track_tqdm=True), | |
| ): | |
| seed = int(randomize_seed_fn(seed, randomize_seed)) | |
| generator = torch.Generator().manual_seed(seed) | |
| if schedule == 'DPM-Solver': | |
| if not isinstance(pipe.scheduler, DPMSolverMultistepScheduler): | |
| pipe.scheduler = DPMSolverMultistepScheduler() | |
| num_inference_steps = dpms_inference_steps | |
| guidance_scale = dpms_guidance_scale | |
| else: | |
| raise ValueError(f"Unknown schedule: {schedule}") | |
| if not use_negative_prompt: | |
| negative_prompt = None # type: ignore | |
| prompt, negative_prompt = apply_style(style, prompt, negative_prompt) | |
| images = pipe( | |
| prompt=prompt, | |
| width=width, | |
| height=height, | |
| negative_prompt=negative_prompt, | |
| guidance_scale=guidance_scale, | |
| num_inference_steps=num_inference_steps, | |
| generator=generator, | |
| num_images_per_prompt=num_imgs, | |
| use_resolution_binning=use_resolution_binning, | |
| output_type="pil", | |
| max_sequence_length=T5_token_max_length, | |
| ).images | |
| image_paths = [save_image(img) for img in images] | |
| print(image_paths) | |
| return image_paths, seed | |
| examples = [ | |
| "A Monkey with a happy face in the Sahara desert.", | |
| "Eiffel Tower was Made up of ICE to look like a cloud, with the bell tower at the top of the building.", | |
| "3D small, round, fluffy creature with big, expressive eyes explores a vibrant, enchanted forest. The creature, a whimsical blend of a rabbit and a squirrel, has soft blue fur and a bushy, striped tail. It hops along a sparkling stream, its eyes wide with wonder. The forest is alive with magical elements: flowers that glow and change colors, trees with leaves in shades of purple and silver, and small floating lights that resemble fireflies. The creature stops to interact playfully with a group of tiny, fairy-like beings dancing around a mushroom ring. The creature looks up in awe at a large, glowing tree that seems to be the heart of the forest.", | |
| "Color photo of a corgi made of transparent glass, standing on the riverside in Yosemite National Park.", | |
| "A close-up photo of a woman. She wore a blue coat with a gray dress underneath. She has blue eyes and blond hair, and wears a pair of earrings. Behind are blurred city buildings and streets.", | |
| "A litter of golden retriever puppies playing in the snow. Their heads pop out of the snow, covered in.", | |
| "a handsome young boy in the middle with sky color background wearing eye glasses, it's super detailed with anime style, it's a portrait with delicated eyes and nice looking face", | |
| "an astronaut sitting in a diner, eating fries, cinematic, analog film", | |
| "Pirate ship trapped in a cosmic maelstrom nebula, rendered in cosmic beach whirlpool engine, volumetric lighting, spectacular, ambient lights, intricate detail.", | |
| "professional portrait photo of an anthropomorphic cat wearing fancy gentleman hat and jacket walking in autumn forest.", | |
| "Outside View from Hotel Made up of Chocolate in space.", | |
| ] | |
| with gr.Blocks(css="style.css") 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.Row(equal_height=False): | |
| 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("Run", scale=0) | |
| result = gr.Gallery(label="Result", columns=NUM_IMAGES_PER_PROMPT, show_label=False) | |
| # with gr.Accordion("Advanced options", open=False): | |
| with gr.Group(): | |
| with gr.Row(): | |
| use_negative_prompt = gr.Checkbox(label="Use negative prompt", value=False, visible=True) | |
| with gr.Row(visible=True): | |
| schedule = gr.Radio( | |
| show_label=True, | |
| container=True, | |
| interactive=True, | |
| choices=SCHEDULE_NAME, | |
| value=DEFAULT_SCHEDULE_NAME, | |
| label="Sampler Schedule", | |
| visible=True, | |
| ) | |
| num_imgs = gr.Slider( | |
| label="Num Images", | |
| minimum=1, | |
| maximum=8, | |
| step=1, | |
| value=1, | |
| ) | |
| style_selection = gr.Radio( | |
| show_label=True, | |
| container=True, | |
| interactive=True, | |
| choices=STYLE_NAMES, | |
| value=DEFAULT_STYLE_NAME, | |
| label="Image Style", | |
| ) | |
| 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=0, | |
| ) | |
| randomize_seed = gr.Checkbox(label="Randomize seed", value=True) | |
| with gr.Row(visible=True): | |
| width = gr.Slider( | |
| label="Width", | |
| minimum=256, | |
| maximum=MAX_IMAGE_SIZE, | |
| step=32, | |
| value=400, | |
| ) | |
| height = gr.Slider( | |
| label="Height", | |
| minimum=256, | |
| maximum=MAX_IMAGE_SIZE, | |
| step=32, | |
| value=400, | |
| ) | |
| with gr.Row(): | |
| dpms_guidance_scale = gr.Slider( | |
| label="Temprature", | |
| minimum=3, | |
| maximum=4, | |
| step=0.1, | |
| value=3.5, | |
| ) | |
| dpms_inference_steps = gr.Slider( | |
| label="Steps", | |
| minimum=5, | |
| maximum=25, | |
| step=1, | |
| value=9, | |
| ) | |
| gr.Examples( | |
| examples=examples, | |
| inputs=prompt, | |
| outputs=[result, seed], | |
| fn=generate, | |
| cache_examples=CACHE_EXAMPLES, | |
| ) | |
| use_negative_prompt.change( | |
| fn=lambda x: gr.update(visible=x), | |
| inputs=use_negative_prompt, | |
| outputs=negative_prompt, | |
| api_name=False, | |
| ) | |
| gr.on( | |
| triggers=[ | |
| prompt.submit, | |
| negative_prompt.submit, | |
| run_button.click, | |
| ], | |
| fn=generate, | |
| inputs=[ | |
| prompt, | |
| negative_prompt, | |
| style_selection, | |
| use_negative_prompt, | |
| num_imgs, | |
| seed, | |
| width, | |
| height, | |
| schedule, | |
| dpms_guidance_scale, | |
| dpms_inference_steps, | |
| randomize_seed, | |
| ], | |
| outputs=[result, seed], | |
| api_name="run", | |
| ) | |
| if __name__ == "__main__": | |
| demo.queue(max_size=20).launch() | |
| # demo.queue(max_size=20).launch(server_name="0.0.0.0", server_port=11900, debug=True) | |