Update app.py

app.py

@@ -1,177 +1,283 @@
-import os
-import gc
-import gradio as gr
-import numpy as np
-import torch
-import json
-import spaces
-import config
-import utils
 import logging
 from PIL import Image, PngImagePlugin
 from datetime import datetime
-from diffusers import StableDiffusionPipeline
+from diffusers.models import AutoencoderKL
+from diffusers import StableDiffusionXLPipeline, StableDiffusionXLImg2ImgPipeline
 
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
 
-DESCRIPTION = "Stable Diffusion 3 Medium Demo"
+DESCRIPTION = "RealVis XL"
 if not torch.cuda.is_available():
     DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU. </p>"
 IS_COLAB = utils.is_google_colab() or os.getenv("IS_COLAB") == "1"
-HF_TOKEN = os.getenv("HF_TOKEN")
-CACHE_EXAMPLES = torch.cuda.is_available() and os.getenv("CACHE_EXAMPLES") == "1"
-MIN_IMAGE_SIZE = int(os.getenv("MIN_IMAGE_SIZE", "512"))
-MAX_IMAGE_SIZE = int(os.getenv("MAX_IMAGE_SIZE", "2048"))
-USE_TORCH_COMPILE = os.getenv("USE_TORCH_COMPILE") == "1"
 ENABLE_CPU_OFFLOAD = os.getenv("ENABLE_CPU_OFFLOAD") == "1"
 OUTPUT_DIR = os.getenv("OUTPUT_DIR", "./outputs")
 
-repo = "stabilityai/stable-diffusion-3-medium-diffusers"
-device = "cuda" if torch.cuda.is_available() else "cpu"
-dtype = torch.float16
+MODEL = os.getenv(
+    "MODEL",
+    "https://huggingface.co/SG161222/RealVisXL_V4.0/blob/main/RealVisXL_V4.0.safetensors",
+)
+
+torch.backends.cudnn.deterministic = True
+torch.backends.cudnn.benchmark = False
+
+device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
+
+def load_pipeline(model_name):
+    vae = AutoencoderKL.from_pretrained(
+        "madebyollin/sdxl-vae-fp16-fix",
+        torch_dtype=torch.float16,
+    )
+    pipeline = (
+        StableDiffusionXLPipeline.from_single_file
+        if MODEL.endswith(".safetensors")
+        else StableDiffusionXLPipeline.from_pretrained
+    )
+
+    pipe = pipeline(
+        model_name,
+        vae=vae,
+        torch_dtype=torch.float16,
+        custom_pipeline="lpw_stable_diffusion_xl",
+        use_safetensors=True,
+        add_watermarker=False,
+        use_auth_token=HF_TOKEN,
+        variant="fp16",
+    )
+
+    pipe.to(device)
+    return pipe
 
 @spaces.GPU
 def generate(
-    prompt: str,
-    negative_prompt: str = "",
-    seed: int = 0,
-    custom_width: int = 1024,
     custom_height: int = 1024,
     guidance_scale: float = 7.0,
     num_inference_steps: int = 30,
-    randomize_seed: bool = True,
+    sampler: str = "DPM++ 2M SDE Karras",
+    aspect_ratio_selector: str = "1024 x 1024",
+    use_upscaler: bool = False,
+    upscaler_strength: float = 0.55,
+    upscale_by: float = 1.5,
     progress=gr.Progress(track_tqdm=True),
 ) -> list:
-    if randomize_seed:
-        seed = np.random.randint(0, np.iinfo(np.int32).max)
-    generator = torch.Generator(device=device).manual_seed(seed)
-
-    images = pipe(
-        prompt=prompt,
-        negative_prompt=negative_prompt,
-        guidance_scale=guidance_scale,
-        num_inference_steps=num_inference_steps,
-        width=custom_width,
-        height=custom_height,
-        generator=generator,
-    ).images
-
-    return images, seed
+    generator = utils.seed_everything(seed)
+
+    width, height = utils.aspect_ratio_handler(
+        aspect_ratio_selector,
+        custom_width,
+        custom_height,
+    )
+
+    width, height = utils.preprocess_image_dimensions(width, height)
+
+    backup_scheduler = pipe.scheduler
+    pipe.scheduler = utils.get_scheduler(pipe.scheduler.config, sampler)
+
+    metadata = {
+        "prompt": prompt,
+        "negative_prompt": negative_prompt,
+        "resolution": f"{width} x {height}",
+        "guidance_scale": guidance_scale,
+        "num_inference_steps": num_inference_steps,
+        "seed": seed,
+        "sampler": sampler,
+        "use_upscaler": use_upscaler,
+        "upscaler_strength": upscaler_strength,
+        "upscale_by": upscale_by,
+    }
+    logger.info(json.dumps(metadata, indent=4))
+
+    try:
+        images = pipe(
+            prompt=prompt,
+            negative_prompt=negative_prompt,
+            width=width,
+            height=height,
+            guidance_scale=guidance_scale,
+            num_inference_steps=num_inference_steps,
+            generator=generator,
+            output_type="pil",
+        ).images
+
+        if use_upscaler:
+            images = [image.resize((int(width * upscale_by), int(height * upscale_by))) for image in images]
+
+        return images, metadata
+    except Exception as e:
+        logger.exception(f"An error occurred: {e}")
+        raise
+    finally:
+        pipe.scheduler = backup_scheduler
+        utils.free_memory()
 
 if torch.cuda.is_available():
-    pipe = StableDiffusionPipeline.from_pretrained(repo, torch_dtype=torch.float16).to(device)
+    pipe = load_pipeline(MODEL)
     logger.info("Loaded on Device!")
 else:
     pipe = None
 
+def postprocess_images(images):
+    return images  # No caption, just return the images
+
 with gr.Blocks(css="style.css") as demo:
     title = gr.HTML(
         f"""<h1><span>{DESCRIPTION}</span></h1>""",
         elem_id="title",
     )
     gr.Markdown(
-        f"""Gradio demo for [Stable Diffusion 3 Medium](https://huggingface.co/stabilityai/stable-diffusion-3-medium)""",
+        f"""Gradio demo for ([RealVis XL]https://huggingface.co/SG161222/RealVisXL_V4.0/)""",
         elem_id="subtitle",
     )
     gr.DuplicateButton(
-        value="Duplicate Space for private use",
-        elem_id="duplicate-button",
-        visible=os.getenv("SHOW_DUPLICATE_BUTTON") == "1",
-    )
-    with gr.Group():
-        with gr.Row():
-            prompt = gr.Text(
-                label="Prompt",
-                show_label=False,
-                max_lines=5,
-                placeholder="Enter your prompt",
-                container=False,
-            )
-            run_button = gr.Button(
-                "Generate", 
-                variant="primary", 
-                scale=0
-            )
-        result = gr.Gallery(
-            label="Result", 
-            columns=1, 
-            preview=True, 
-            show_label=False
-        )
-    with gr.Accordion(label="Advanced Settings", open=False):
-        negative_prompt = gr.Text(
-            label="Negative Prompt",
-            max_lines=5,
             placeholder="Enter a negative prompt",
             value=""
         )
-        custom_width = gr.Slider(
-            label="Width",
-            minimum=MIN_IMAGE_SIZE,
-            maximum=MAX_IMAGE_SIZE,
-            step=64,
-            value=1024,
-        )
-        custom_height = gr.Slider(
-            label="Height",
-            minimum=MIN_IMAGE_SIZE,
-            maximum=MAX_IMAGE_SIZE,
-            step=64,
-            value=1024,
+        aspect_ratio_selector = gr.Radio(
+            label="Aspect Ratio",
+            choices=config.aspect_ratios,
+            value="1024 x 1024",
+            container=True,
+
         )
-        with gr.Row():
-            guidance_scale = gr.Slider(
-                label="Guidance scale",
-                minimum=1,
-                maximum=12,
-                step=0.1,
-                value=7.0,
+        with gr.Group(visible=False) as custom_resolution:
+            with gr.Row():
+                custom_width = gr.Slider(
+                    label="Width",
+                    minimum=MIN_IMAGE_SIZE,
+                    maximum=MAX_IMAGE_SIZE,
+                    step=8,
+                    value=1024,
+                )
+                custom_height = gr.Slider(
+                    label="Height",
+                    minimum=MIN_IMAGE_SIZE,
+                    maximum=MAX_IMAGE_SIZE,
+                    step=8,
+                    value=1024,
+                )
+        use_upscaler = gr.Checkbox(label="Use Upscaler", value=False)
+        with gr.Row() as upscaler_row:
+            upscaler_strength = gr.Slider(
+                label="Strength",
+                minimum=0,
+                maximum=1,
+                step=0.05,
+                value=0.55,
+                visible=False,
             )
-            num_inference_steps = gr.Slider(
-                label="Number of inference steps",
+            upscale_by = gr.Slider(
+                label="Upscale by",
                 minimum=1,
-                maximum=100,
-                step=1,
-                value=30,
+                maximum=1.5,
+                step=0.1,
+                value=1.5,
+                visible=False,
             )
-        seed = gr.Slider(
-            label="Seed", minimum=0, maximum=np.iinfo(np.int32).max, step=1, value=0
+
+        sampler = gr.Dropdown(
+            label="Sampler",
+            choices=config.sampler_list,
+            interactive=True,
+            value="DPM++ 2M SDE Karras",
         )
-        randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
+        with gr.Row():
+            seed = gr.Slider(
+                label="Seed", minimum=0, maximum=utils.MAX_SEED, step=1, value=0
+            )
+            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
+        with gr.Group():
+            with gr.Row():
+                guidance_scale = gr.Slider(
+                    label="Guidance scale",
+                    minimum=1,
+                    maximum=12,
+                    step=0.1,
+                    value=7.0,
+                )
+                num_inference_steps = gr.Slider(
+                    label="Number of inference steps",
+                    minimum=1,
+                    maximum=100,
+                    step=1,
+                    value=28,
+                )
+    with gr.Accordion(label="Generation Parameters", open=False):
+        gr_metadata = gr.JSON(label="Metadata", show_label=False)
     gr.Examples(
-        examples=[
-            "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
-            "An astronaut riding a green horse",
-            "A delicious ceviche cheesecake slice",
-        ],
+        examples=config.examples,
+
+
+
+
         inputs=prompt,
-        outputs=result,
+        outputs=[result, gr_metadata],
+        fn=lambda *args, **kwargs: generate(*args, use_upscaler=True, **kwargs),
+        cache_examples=CACHE_EXAMPLES,
     )
+    use_upscaler.change(
+        fn=lambda x: [gr.update(visible=x), gr.update(visible=x)],
+        inputs=use_upscaler,
+        outputs=[upscaler_strength, upscale_by],
+        queue=False,
+        api_name=False,
+    )
+    aspect_ratio_selector.change(
+        fn=lambda x: gr.update(visible=x == "Custom"),
+        inputs=aspect_ratio_selector,
+        outputs=custom_resolution,
+        queue=False,
+        api_name=False,
+    )
+
     inputs = [
         prompt,
         negative_prompt,
-        seed,
-        custom_width,
         custom_height,
         guidance_scale,
         num_inference_steps,
-        randomize_seed,
+        sampler,
+        aspect_ratio_selector,
+        use_upscaler,
+        upscaler_strength,
+        upscale_by,
     ]
+
     prompt.submit(
+        fn=utils.randomize_seed_fn,
+        inputs=[seed, randomize_seed],
+        outputs=seed,
+        queue=False,
+        api_name=False,
+    ).then(
         fn=generate,
         inputs=inputs,
-        outputs=[result, seed],
+        outputs=[result, gr_metadata],
+        api_name="run",
     )
     negative_prompt.submit(
+        fn=utils.randomize_seed_fn,
+        inputs=[seed, randomize_seed],
+        outputs=seed,
+        queue=False,
+        api_name=False,
+    ).then(
         fn=generate,
         inputs=inputs,
-        outputs=[result, seed],
+        outputs=[result, gr_metadata],
+        api_name=False,
     )
     run_button.click(
+        fn=utils.randomize_seed_fn,
+        inputs=[seed, randomize_seed],
+        outputs=seed,
+        queue=False,
+        api_name=False,
+    ).then(
         fn=generate,
         inputs=inputs,
-        outputs=[result, seed],
+        outputs=[result, gr_metadata],
+        api_name=False,
     )
 
-demo.queue(max_size=20).launch(debug=IS_COLAB, share=IS_COLAB, show_error=True)
+demo.queue(max_size=20).launch(debug=IS_COLAB, share=IS_COLAB, show_error=True)