Update app.py

app.py

@@ -1,160 +1,91 @@
-#!/usr/bin/env python
-
 import os
 import random
 import uuid
+import json
 
 import gradio as gr
 import numpy as np
 from PIL import Image
 import spaces
-from typing import Tuple
 import torch
-from diffusers import StableDiffusionXLPipeline, EulerAncestralDiscreteScheduler, AutoencoderKL
-
-DESCRIPTION = """
-# OpenDalle V1.1
-"""
-
-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
-
-MAX_SEED = np.iinfo(np.int32).max
+from diffusers import StableDiffusionXLPipeline, EulerAncestralDiscreteScheduler
 
 if not torch.cuda.is_available():
     DESCRIPTION += "\n<p>Running on CPU 🥶 This demo may 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", "4096"))
+USE_TORCH_COMPILE = os.getenv("USE_TORCH_COMPILE", "0") == "1"
+ENABLE_CPU_OFFLOAD = os.getenv("ENABLE_CPU_OFFLOAD", "0") == "1"
 
-USE_TORCH_COMPILE = 0
-ENABLE_CPU_OFFLOAD = 0
-
+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 = StableDiffusionXLPipeline.from_pretrained(
         "dataautogpt3/OpenDalleV1.1",
-        vae=vae,
         torch_dtype=torch.float16,
         use_safetensors=True,
+        add_watermarker=False
     )
+    pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config)
     pipe.to("cuda")
 
 
-# by PixArt-alpha/PixArt-Sigma    
-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": "Photographic",
-        "prompt": "cinematic photo {prompt} . 35mm photograph, film, bokeh, professional, 4k, highly detailed",
-        "negative_prompt": "drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly",
-    },
-    {
-        "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)"
+def save_image(img):
+    unique_name = str(uuid.uuid4()) + ".png"
+    img.save(unique_name)
+    return unique_name
 
-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
+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)
+@spaces.GPU(duration=30, queue=False)
 def generate(
     prompt: str,
     negative_prompt: str = "",
-    style: str = DEFAULT_STYLE_NAME,
     use_negative_prompt: bool = False,
-    num_inference_steps: int = 30,
-    num_images_per_prompt: int = 2,
-    seed: int = 0,
+    seed: int = 1,
     width: int = 1024,
     height: int = 1024,
     guidance_scale: float = 3,
+    num_inference_steps: int = 30,
     randomize_seed: bool = False,
+    use_resolution_binning: bool = True,
     progress=gr.Progress(track_tqdm=True),
 ):
-
-    
+    pipe.to(device)
     seed = int(randomize_seed_fn(seed, randomize_seed))
+    generator = torch.Generator().manual_seed(seed)   
+
+    options = {
+        "prompt":prompt,
+        "negative_prompt":negative_prompt,
+        "width":width,
+        "height":height,
+        "guidance_scale":guidance_scale,
+        "num_inference_steps":num_inference_steps,
+        "generator":generator,
+        "use_resolution_binning":use_resolution_binning,
+        "output_type":"pil",
+
+    }
+    
+    images = pipe(**options).images
 
-    if not use_negative_prompt:
-        negative_prompt = ""  # type: ignore
-    prompt, negative_prompt = apply_style(style, prompt, negative_prompt)
-
-    images = pipe(
-        prompt=prompt,
-        negative_prompt=negative_prompt,
-        width=width,
-        height=height,
-        guidance_scale=guidance_scale,
-        num_inference_steps=num_inference_steps,
-        num_images_per_prompt=num_images_per_prompt,
-        cross_attention_kwargs={"scale": 0.65},
-        output_type="pil",
-    ).images
     image_paths = [save_image(img) for img in images]
-    print(image_paths)
     return image_paths, seed
 
+
 examples = [
-    "black fluffy gorgeous dangerous cat animal creature, large orange eyes, big fluffy ears, piercing gaze, full moon, dark ambiance, best quality, extremely detailed",
-    "an anime female general laughing, with a military cap, evil smile, sadistic, grim",
-    "Super Closeup Portrait, action shot, Profoundly dark whitish meadow, glass flowers, Stains, space grunge style, Jeanne d'Arc wearing White Olive green used styled Cotton frock, Wielding thin silver sword, Sci-fi vibe, dirty, noisy, Vintage monk style, very detailed, hd",
-    "((OpenDAlle!)text logo:1), ~*~aesthetic~*~",
-    "John Berkey Style page,ral-oilspill, There is no road ahead,no land, Strangely,the river is still flowing,crossing the void into the mysterious unknown, The end of nothingness,a huge ripple,it is a kind of wave,and it is the law of time that lasts forever in that void, At the end of the infinite void,there is a colorful world,very hazy and mysterious,and it cannot be seen clearly,but it is real, And that's where the river goes",
+    "a cat eating a piece of cheese",
+    "a ROBOT riding a BLUE horse on Mars, photorealistic, 4k",
+    "Ironman VS Hulk, ultrarealistic",
+    "Astronaut in a jungle, cold color palette, oil pastel, detailed, 8k",
+    "An alien holding sign board contain word 'Flash', futuristic, neonpunk",
+    "Kids going to school, Anime style"
 ]
 
 css = '''
@@ -164,14 +95,9 @@ footer {
     visibility: hidden
 }
 '''
-with gr.Blocks(css=css, theme=gr.themes.Base()) as demo:
-    gr.Markdown(DESCRIPTION)
-    gr.DuplicateButton(
-        value="Duplicate Space for private use",
-        elem_id="duplicate-button",
-        visible=False,
-    )
-
+with gr.Blocks(css=css) as demo:
+    gr.Markdown("""# SDXL Flash
+        ### First Image processing takes time then images generate faster.""")
     with gr.Group():
         with gr.Row():
             prompt = gr.Text(
@@ -181,81 +107,64 @@ with gr.Blocks(css=css, theme=gr.themes.Base()) as demo:
                 placeholder="Enter your prompt",
                 container=False,
             )
-            run_button = gr.Button("Run")
-        result = gr.Gallery(label="Result", columns=1, preview=True)
+            run_button = gr.Button("Run", scale=0)
+        result = gr.Gallery(label="Result", columns=1)
     with gr.Accordion("Advanced options", open=False):
-        use_negative_prompt = gr.Checkbox(label="Use negative prompt", value=False, visible=True)
-        negative_prompt = gr.Text(
+        with gr.Row():
+            use_negative_prompt = gr.Checkbox(label="Use negative prompt", value=True)
+            negative_prompt = gr.Text(
                 label="Negative prompt",
-                max_lines=1,
+                max_lines=5,
+                lines=4,
                 placeholder="Enter a negative prompt",
+                value="(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, NSFW",
                 visible=True,
             )
-        with gr.Row():
-            num_inference_steps = gr.Slider(
-                label="Steps",
-                minimum=10,
-                maximum=60,
-                step=1,
-                value=30,
-            )
-        with gr.Row():
-            num_images_per_prompt = gr.Slider(
-                label="Images",
-                minimum=1,
-                maximum=5,
-                step=1,
-                value=2,
-            )
         seed = gr.Slider(
             label="Seed",
             minimum=0,
             maximum=MAX_SEED,
             step=1,
             value=0,
-            visible=True
         )
         randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
         with gr.Row(visible=True):
             width = gr.Slider(
                 label="Width",
                 minimum=512,
-                maximum=2048,
-                step=8,
+                maximum=MAX_IMAGE_SIZE,
+                step=64,
                 value=1024,
             )
             height = gr.Slider(
                 label="Height",
                 minimum=512,
-                maximum=2048,
-                step=8,
+                maximum=MAX_IMAGE_SIZE,
+                step=64,
                 value=1024,
             )
         with gr.Row():
             guidance_scale = gr.Slider(
                 label="Guidance Scale",
                 minimum=0.1,
-                maximum=20.0,
+                maximum=6,
                 step=0.1,
-                value=6,
+                value=3.0,
             )
-    with gr.Row(visible=True):
-            style_selection = gr.Radio(
-                show_label=True,
-                container=True,
-                interactive=True,
-                choices=STYLE_NAMES,
-                value=DEFAULT_STYLE_NAME,
-                label="Image Style",
+            num_inference_steps = gr.Slider(
+                label="Number of inference steps",
+                minimum=1,
+                maximum=15,
+                step=1,
+                value=8,
             )
-        
 
     gr.Examples(
         examples=examples,
         inputs=prompt,
         outputs=[result, seed],
         fn=generate,
-        cache_examples=False,
+        cache_examples=CACHE_EXAMPLES,
     )
 
     use_negative_prompt.change(
@@ -264,7 +173,6 @@ with gr.Blocks(css=css, theme=gr.themes.Base()) as demo:
         outputs=negative_prompt,
         api_name=False,
     )
-    
 
     gr.on(
         triggers=[
@@ -276,19 +184,17 @@ with gr.Blocks(css=css, theme=gr.themes.Base()) as demo:
         inputs=[
             prompt,
             negative_prompt,
-            style_selection,
             use_negative_prompt,
-            num_inference_steps,
-            num_images_per_prompt,
             seed,
             width,
             height,
             guidance_scale,
+            num_inference_steps,
             randomize_seed,
         ],
         outputs=[result, seed],
         api_name="run",
     )
-    
+
 if __name__ == "__main__":
-    demo.queue(max_size=20).launch(show_api=True, debug=False, share=True)
+    demo.queue(max_size=20).launch()