improve

app.py

@@ -1,244 +1,216 @@
-from diffusers import AutoencoderKL, UNet2DConditionModel, StableDiffusionPipeline, StableDiffusionImg2ImgPipeline, DPMSolverMultistepScheduler
+from diffusers import (
+    StableDiffusionPipeline,
+    StableDiffusionImg2ImgPipeline,
+    DPMSolverMultistepScheduler,
+)
 import gradio as gr
 import torch
 from PIL import Image
-import utils
-import datetime
 import time
 import psutil
 import random
 
 
 start_time = time.time()
-is_colab = utils.is_google_colab()
-state = None
 current_steps = 25
 
+
 class Model:
     def __init__(self, name, path=""):
         self.name = name
         self.path = path
-        self.pipe_t2i = None
-        self.pipe_i2i = None
-
-models = [
-     Model("2.2", "darkstorm2150/Protogen_v2.2_Official_Release"),
-     Model("3.4", "darkstorm2150/Protogen_x3.4_Official_Release"),
-     Model("5.3", "darkstorm2150/Protogen_v5.3_Official_Release"),
-     Model("5.8", "darkstorm2150/Protogen_x5.8_Official_Release"),
-     Model("Dragon", "darkstorm2150/Protogen_Dragon_Official_Release"),
-  ]
-
-custom_model = None
-if is_colab:
-  models.insert(0, Model("Custom model"))
-  custom_model = models[0]
-
-last_mode = "txt2img"
-current_model = models[1] if is_colab else models[0]
-current_model_path = current_model.path
-
-if is_colab:
-  pipe = StableDiffusionPipeline.from_pretrained(
-      current_model.path,
-      torch_dtype=torch.float16,
-      scheduler=DPMSolverMultistepScheduler.from_pretrained(current_model.path, subfolder="scheduler"),
-      safety_checker=lambda images, clip_input: (images, False)
-      )
-
-else:
-  pipe = StableDiffusionPipeline.from_pretrained(
-      current_model.path,
-      torch_dtype=torch.float16,
-      scheduler=DPMSolverMultistepScheduler.from_pretrained(current_model.path, subfolder="scheduler")
-      )
-    
-if torch.cuda.is_available():
-  pipe = pipe.to("cuda")
-  pipe.enable_xformers_memory_efficient_attention()
-
-device = "GPU 🔥" if torch.cuda.is_available() else "CPU 🥶"
-
-def error_str(error, title="Error"):
-    return f"""#### {title}
-            {error}"""  if error else ""
-
-def update_state(new_state):
-  global state
-  state = new_state
-
-def update_state_info(old_state):
-  if state and state != old_state:
-    return gr.update(value=state)
-
-def custom_model_changed(path):
-  models[0].path = path
-  global current_model
-  current_model = models[0]
-
-def on_model_change(model_name):
-  
-  prefix = "Enter prefix"
-
-  return gr.update(visible = model_name == models[0].name), gr.update(placeholder=prefix)
-
-def on_steps_change(steps):
-  global current_steps
-  current_steps = steps
 
-def pipe_callback(step: int, timestep: int, latents: torch.FloatTensor):
-    update_state(f"{step}/{current_steps} steps")#\nTime left, sec: {timestep/100:.0f}")
-
-def inference(model_name, prompt, guidance, steps, n_images=1, width=512, height=512, seed=0, img=None, strength=0.5, neg_prompt=""):
-
-  update_state(" ")
+        if path != "":
+            self.pipe_t2i = StableDiffusionPipeline.from_pretrained(
+                path, torch_dtype=torch.float16
+            )
+            self.pipe_i2i.scheduler = DPMSolverMultistepScheduler.from_config(
+                self.pipe_t2i.scheduler.config
+            )
+            self.pipe_i2i = StableDiffusionImg2ImgPipeline(
+                **self.pipe_t2i.components, torch_dtype=torch.float16
+            )
+        else:
+            self.pipe_t2i = None
+            self.pipe_i2i = None
 
-  print(psutil.virtual_memory()) # print memory usage
 
-  global current_model
-  for model in models:
-    if model.name == model_name:
-      current_model = model
-      model_path = current_model.path
+models = [
+    Model("2.2", "darkstorm2150/Protogen_v2.2_Official_Release"),
+    Model("3.4", "darkstorm2150/Protogen_x3.4_Official_Release"),
+#    Model("5.3", "darkstorm2150/Protogen_v5.3_Official_Release"),
+#    Model("5.8", "darkstorm2150/Protogen_x5.8_Official_Release"),
+#    Model("Dragon", "darkstorm2150/Protogen_Dragon_Official_Release"),
+]
 
-  # generator = torch.Generator('cuda').manual_seed(seed) if seed != 0 else None
-  if seed == 0:
-    seed = random.randint(0, 2147483647)
+MODELS = {m.name: m for m in models}
 
-  generator = torch.Generator('cuda').manual_seed(seed)
+device = "GPU 🔥" if torch.cuda.is_available() else "CPU 🥶"
 
-  try:
-    if img is not None:
-      return img_to_img(model_path, prompt, n_images, neg_prompt, img, strength, guidance, steps, width, height, generator, seed), f"Done. Seed: {seed}"
-    else:
-      return txt_to_img(model_path, prompt, n_images, neg_prompt, guidance, steps, width, height, generator, seed), f"Done. Seed: {seed}"
-  except Exception as e:
-    return None, error_str(e)
 
-def txt_to_img(model_path, prompt, n_images, neg_prompt, guidance, steps, width, height, generator, seed):
+# if torch.cuda.is_available():
+#  pipe = pipe.to("cuda")
+#  pipe.enable_xformers_memory_efficient_attention()
 
-    print(f"{datetime.datetime.now()} txt_to_img, model: {current_model.name}")
 
-    global last_mode
-    global pipe
-    global current_model_path
-    if model_path != current_model_path or last_mode != "txt2img":
-        current_model_path = model_path
+def error_str(error, title="Error"):
+    return (
+        f"""#### {title}
+            {error}"""
+        if error
+        else ""
+    )
 
-        update_state(f"Loading {current_model.name} text-to-image model...")
 
-        if is_colab or current_model == custom_model:
-          pipe = StableDiffusionPipeline.from_pretrained(
-              current_model_path,
-              torch_dtype=torch.float16,
-              scheduler=DPMSolverMultistepScheduler.from_pretrained(current_model.path, subfolder="scheduler"),
-              safety_checker=lambda images, clip_input: (images, False)
-              )
+def inference(
+    model_name,
+    prompt,
+    guidance,
+    steps,
+    n_images=1,
+    width=512,
+    height=512,
+    seed=0,
+    img=None,
+    strength=0.5,
+    neg_prompt="",
+):
+
+    print(psutil.virtual_memory())  # print memory usage
+
+    if seed == 0:
+        seed = random.randint(0, 2147483647)
+
+    generator = torch.Generator("cuda").manual_seed(seed)
+
+    try:
+        if img is not None:
+            return (
+                img_to_img(
+                    model_name,
+                    prompt,
+                    n_images,
+                    neg_prompt,
+                    img,
+                    strength,
+                    guidance,
+                    steps,
+                    width,
+                    height,
+                    generator,
+                    seed,
+                ),
+                f"Done. Seed: {seed}",
+            )
         else:
-          pipe = StableDiffusionPipeline.from_pretrained(
-              current_model_path,
-              torch_dtype=torch.float16,
-              scheduler=DPMSolverMultistepScheduler.from_pretrained(current_model.path, subfolder="scheduler")
-              )
-          # pipe = pipe.to("cpu")
-          # pipe = current_model.pipe_t2i
-
-        if torch.cuda.is_available():
-          pipe = pipe.to("cuda")
-          pipe.enable_xformers_memory_efficient_attention()
-        last_mode = "txt2img"
+            return (
+                txt_to_img(
+                    model_name,
+                    prompt,
+                    n_images,
+                    neg_prompt,
+                    guidance,
+                    steps,
+                    width,
+                    height,
+                    generator,
+                    seed,
+                ),
+                f"Done. Seed: {seed}",
+            )
+    except Exception as e:
+        return None, error_str(e)
+
+
+def txt_to_img(
+    model_name,
+    prompt,
+    n_images,
+    neg_prompt,
+    guidance,
+    steps,
+    width,
+    height,
+    generator,
+    seed,
+):
+    pipe = MODELS[model_name].pipe_t2i
+
+    if torch.cuda.is_available():
+        pipe = pipe.to("cuda")
+        pipe.enable_xformers_memory_efficient_attention()
 
     result = pipe(
-      prompt,
-      negative_prompt = neg_prompt,
-      num_images_per_prompt=n_images,
-      num_inference_steps = int(steps),
-      guidance_scale = guidance,
-      width = width,
-      height = height,
-      generator = generator,
-      callback=pipe_callback)
-
-    # update_state(f"Done. Seed: {seed}")
-    
-    return replace_nsfw_images(result)
-
-def img_to_img(model_path, prompt, n_images, neg_prompt, img, strength, guidance, steps, width, height, generator, seed):
+        prompt,
+        negative_prompt=neg_prompt,
+        num_images_per_prompt=n_images,
+        num_inference_steps=int(steps),
+        guidance_scale=guidance,
+        width=width,
+        height=height,
+        generator=generator,
+    )
 
-    print(f"{datetime.datetime.now()} img_to_img, model: {model_path}")
+    pipe.to("cpu")
 
-    global last_mode
-    global pipe
-    global current_model_path
-    if model_path != current_model_path or last_mode != "img2img":
-        current_model_path = model_path
+    return replace_nsfw_images(result)
 
-        update_state(f"Loading {current_model.name} image-to-image model...")
 
-        if is_colab or current_model == custom_model:
-          pipe = StableDiffusionImg2ImgPipeline.from_pretrained(
-              current_model_path,
-              torch_dtype=torch.float16,
-              scheduler=DPMSolverMultistepScheduler.from_pretrained(current_model.path, subfolder="scheduler"),
-              safety_checker=lambda images, clip_input: (images, False)
-              )
-        else:
-          pipe = StableDiffusionImg2ImgPipeline.from_pretrained(
-              current_model_path,
-              torch_dtype=torch.float16,
-              scheduler=DPMSolverMultistepScheduler.from_pretrained(current_model.path, subfolder="scheduler")
-              )
-          # pipe = pipe.to("cpu")
-          # pipe = current_model.pipe_i2i
-        
-        if torch.cuda.is_available():
-          pipe = pipe.to("cuda")
-          pipe.enable_xformers_memory_efficient_attention()
-        last_mode = "img2img"
+def img_to_img(
+    model_name,
+    prompt,
+    n_images,
+    neg_prompt,
+    img,
+    strength,
+    guidance,
+    steps,
+    width,
+    height,
+    generator,
+    seed,
+):
+    pipe = MODELS[model_name].pipe_i2i
+
+    if torch.cuda.is_available():
+        pipe = pipe.to("cuda")
+        pipe.enable_xformers_memory_efficient_attention()
 
     ratio = min(height / img.height, width / img.width)
     img = img.resize((int(img.width * ratio), int(img.height * ratio)), Image.LANCZOS)
+
     result = pipe(
         prompt,
-        negative_prompt = neg_prompt,
+        negative_prompt=neg_prompt,
         num_images_per_prompt=n_images,
-        image = img,
-        num_inference_steps = int(steps),
-        strength = strength,
-        guidance_scale = guidance,
-        # width = width,
-        # height = height,
-        generator = generator,
-        callback=pipe_callback)
-
-    # update_state(f"Done. Seed: {seed}")
-        
+        image=img,
+        num_inference_steps=int(steps),
+        strength=strength,
+        guidance_scale=guidance,
+        generator=generator,
+    )
+
+    pipe.to("cpu")
+
     return replace_nsfw_images(result)
 
-def replace_nsfw_images(results):
 
-    if is_colab:
-      return results.images
-      
+def replace_nsfw_images(results):
     for i in range(len(results.images)):
-      if results.nsfw_content_detected[i]:
-        results.images[i] = Image.open("nsfw.png")
+        if results.nsfw_content_detected[i]:
+            results.images[i] = Image.open("nsfw.png")
     return results.images
 
-# css = """.finetuned-diffusion-div div{display:inline-flex;align-items:center;gap:.8rem;font-size:1.75rem}.finetuned-diffusion-div div h1{font-weight:900;margin-bottom:7px}.finetuned-diffusion-div p{margin-bottom:10px;font-size:94%}a{text-decoration:underline}.tabs{margin-top:0;margin-bottom:0}#gallery{min-height:20rem}
-# """
+
 with gr.Blocks(css="style.css") as demo:
     gr.HTML(
-        f"""
+        """
             <div class="finetuned-diffusion-div">
               <div>
                 <h1>Protogen Diffusion</h1>
               </div>
               <p>
-               Demo for multiple fine-tuned Protogen Stable Diffusion models + in colab notebook you can load any other Diffusers 🧨 SD model hosted on HuggingFace 🤗.
-              </p>
-              <p>You can skip the queue and load custom models in the colab: <a href="https://colab.research.google.com/gist/qunash/42112fb104509c24fd3aa6d1c11dd6e0/copy-of-fine-tuned-diffusion-gradio.ipynb"><img data-canonical-src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab" src="https://camo.githubusercontent.com/84f0493939e0c4de4e6dbe113251b4bfb5353e57134ffd9fcab6b8714514d4d1/68747470733a2f2f636f6c61622e72657365617263682e676f6f676c652e636f6d2f6173736574732f636f6c61622d62616467652e737667"></a></p>
-               Running on <b>{device}</b>{(" in a <b>Google Colab</b>." if is_colab else "")}
+               Demo for multiple fine-tuned Protogen Stable Diffusion models.
               </p>
               <p>You can also duplicate this space and upgrade to gpu by going to settings:<br>
               <a style="display:inline-block" href="https://huggingface.co/spaces/patrickvonplaten/finetuned_diffusion?duplicate=true"><img src="https://img.shields.io/badge/-Duplicate%20Space-blue?labelColor=white&style=flat&logo=data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAAAAXNSR0IArs4c6QAAAP5JREFUOE+lk7FqAkEURY+ltunEgFXS2sZGIbXfEPdLlnxJyDdYB62sbbUKpLbVNhyYFzbrrA74YJlh9r079973psed0cvUD4A+4HoCjsA85X0Dfn/RBLBgBDxnQPfAEJgBY+A9gALA4tcbamSzS4xq4FOQAJgCDwV2CPKV8tZAJcAjMMkUe1vX+U+SMhfAJEHasQIWmXNN3abzDwHUrgcRGmYcgKe0bxrblHEB4E/pndMazNpSZGcsZdBlYJcEL9Afo75molJyM2FxmPgmgPqlWNLGfwZGG6UiyEvLzHYDmoPkDDiNm9JR9uboiONcBXrpY1qmgs21x1QwyZcpvxt9NS09PlsPAAAAAElFTkSuQmCC&logoWidth=14" alt="Duplicate Space"></a></p>
@@ -246,64 +218,124 @@ with gr.Blocks(css="style.css") as demo:
         """
     )
     with gr.Row():
-        
-        with gr.Column(scale=55):
-          with gr.Group():
-              model_name = gr.Dropdown(label="Model", choices=[m.name for m in models], value=current_model.name)
-              with gr.Box(visible=False) as custom_model_group:
-                custom_model_path = gr.Textbox(label="Custom model path", placeholder="Path to model, e.g. darkstorm2150/Protogen_x3.4_Official_Release", interactive=True)
-                gr.HTML("<div><font size='2'>Custom models have to be downloaded first, so give it some time.</font></div>")
-              
-              with gr.Row():
-                prompt = gr.Textbox(label="Prompt", show_label=False, max_lines=2,placeholder="Enter prompt.").style(container=False)
-                generate = gr.Button(value="Generate").style(rounded=(False, True, True, False))
-
-
-              # image_out = gr.Image(height=512)
-              gallery = gr.Gallery(label="Generated images", show_label=False, elem_id="gallery").style(grid=[2], height="auto")
-          
-          state_info = gr.Textbox(label="State", show_label=False, max_lines=2).style(container=False)
-          error_output = gr.Markdown()
 
-        with gr.Column(scale=45):
-          with gr.Tab("Options"):
+        with gr.Column(scale=55):
             with gr.Group():
-              neg_prompt = gr.Textbox(label="Negative prompt", placeholder="What to exclude from the image")
+                model_name = gr.Dropdown(
+                    label="Model",
+                    choices=[m.name for m in models],
+                    value=models[0].name,
+                )
+                with gr.Box(visible=False) as custom_model_group:
+                    custom_model_path = gr.Textbox(
+                        label="Custom model path",
+                        placeholder="Path to model, e.g. darkstorm2150/Protogen_x3.4_Official_Release",
+                        interactive=True,
+                    )
+                    gr.HTML(
+                        "<div><font size='2'>Custom models have to be downloaded first, so give it some time.</font></div>"
+                    )
+
+                with gr.Row():
+                    prompt = gr.Textbox(
+                        label="Prompt",
+                        show_label=False,
+                        max_lines=2,
+                        placeholder="Enter prompt.",
+                    ).style(container=False)
+                    generate = gr.Button(value="Generate").style(
+                        rounded=(False, True, True, False)
+                    )
+
+                # image_out = gr.Image(height=512)
+                gallery = gr.Gallery(
+                    label="Generated images", show_label=False, elem_id="gallery"
+                ).style(grid=[2], height="auto")
+
+            state_info = gr.Textbox(label="State", show_label=False, max_lines=2).style(
+                container=False
+            )
+            error_output = gr.Markdown()
 
-              n_images = gr.Slider(label="Images", value=1, minimum=1, maximum=4, step=1)
-
-              with gr.Row():
-                guidance = gr.Slider(label="Guidance scale", value=7.5, maximum=15)
-                steps = gr.Slider(label="Steps", value=current_steps, minimum=2, maximum=75, step=1)
-
-              with gr.Row():
-                width = gr.Slider(label="Width", value=512, minimum=64, maximum=1024, step=8)
-                height = gr.Slider(label="Height", value=512, minimum=64, maximum=1024, step=8)
-
-              seed = gr.Slider(0, 2147483647, label='Seed (0 = random)', value=0, step=1)
-
-          with gr.Tab("Image to image"):
-              with gr.Group():
-                image = gr.Image(label="Image", height=256, tool="editor", type="pil")
-                strength = gr.Slider(label="Transformation strength", minimum=0, maximum=1, step=0.01, value=0.5)
-
-    if is_colab:
-        model_name.change(on_model_change, inputs=model_name, outputs=[custom_model_group, prompt], queue=False)
-        custom_model_path.change(custom_model_changed, inputs=custom_model_path, outputs=None)
-    # n_images.change(lambda n: gr.Gallery().style(grid=[2 if n > 1 else 1], height="auto"), inputs=n_images, outputs=gallery)
-    steps.change(on_steps_change, inputs=[steps], outputs=[], queue=False)
-
-    inputs = [model_name, prompt, guidance, steps, n_images, width, height, seed, image, strength, neg_prompt]
+        with gr.Column(scale=45):
+            with gr.Tab("Options"):
+                with gr.Group():
+                    neg_prompt = gr.Textbox(
+                        label="Negative prompt",
+                        placeholder="What to exclude from the image",
+                    )
+
+                    n_images = gr.Slider(
+                        label="Images", value=1, minimum=1, maximum=4, step=1
+                    )
+
+                    with gr.Row():
+                        guidance = gr.Slider(
+                            label="Guidance scale", value=7.5, maximum=15
+                        )
+                        steps = gr.Slider(
+                            label="Steps",
+                            value=current_steps,
+                            minimum=2,
+                            maximum=75,
+                            step=1,
+                        )
+
+                    with gr.Row():
+                        width = gr.Slider(
+                            label="Width", value=512, minimum=64, maximum=1024, step=8
+                        )
+                        height = gr.Slider(
+                            label="Height", value=512, minimum=64, maximum=1024, step=8
+                        )
+
+                    seed = gr.Slider(
+                        0, 2147483647, label="Seed (0 = random)", value=0, step=1
+                    )
+
+            with gr.Tab("Image to image"):
+                with gr.Group():
+                    image = gr.Image(
+                        label="Image", height=256, tool="editor", type="pil"
+                    )
+                    strength = gr.Slider(
+                        label="Transformation strength",
+                        minimum=0,
+                        maximum=1,
+                        step=0.01,
+                        value=0.5,
+                    )
+
+    inputs = [
+        model_name,
+        prompt,
+        guidance,
+        steps,
+        n_images,
+        width,
+        height,
+        seed,
+        image,
+        strength,
+        neg_prompt,
+    ]
     outputs = [gallery, error_output]
     prompt.submit(inference, inputs=inputs, outputs=outputs)
     generate.click(inference, inputs=inputs, outputs=outputs)
 
-    ex = gr.Examples([
-        [models[2].name, "Brad Pitt with sunglasses, highly realistic", 7.5, 25],
-        [models[0].name, "portrait of a beautiful alyx vance half life", 10, 25],
-    ], inputs=[model_name, prompt, guidance, steps], outputs=outputs, fn=inference, cache_examples=False)
+    ex = gr.Examples(
+        [
+            [models[2].name, "Brad Pitt with sunglasses, highly realistic", 7.5, 25],
+            [models[0].name, "portrait of a beautiful alyx vance half life", 10, 25],
+        ],
+        inputs=[model_name, prompt, guidance, steps],
+        outputs=outputs,
+        fn=inference,
+        cache_examples=False,
+    )
 
-    gr.HTML("""
+    gr.HTML(
+        """
     <div style="border-top: 1px solid #303030;">
       <br>
       <p>Models by <a href="https://huggingface.co/darkstorm2150">@darkstorm2150</a> and others. ❤️</p>
@@ -311,12 +343,10 @@ with gr.Blocks(css="style.css") as demo:
       <p>Space by: Darkstorm (Victor Espinoza)<br>
       <a href="https://www.instagram.com/officialvictorespinoza/">Instagram</a>
     </div>
-    """)
-
-    demo.load(update_state_info, inputs=state_info, outputs=state_info, every=0.5, show_progress=False)
+    """
+    )
 
 print(f"Space built in {time.time() - start_time:.2f} seconds")
 
-# if not is_colab:
 demo.queue(concurrency_count=1)
-demo.launch(debug=is_colab, share=is_colab)
+demo.launch()