finalize

README.md

@@ -1,12 +1,14 @@
 ---
-title: Protogen Web Ui
-emoji: 😻
-colorFrom: indigo
+title: Finetuned Diffusion
+emoji: 🪄🖼️
+colorFrom: red
 colorTo: pink
 sdk: gradio
-sdk_version: 3.16.1
+sdk_version: 3.15.0
 app_file: app.py
-pinned: false
+pinned: true
+license: mit
+duplicated_from: anzorq/finetuned_diffusion
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,323 @@
+from diffusers import AutoencoderKL, UNet2DConditionModel, 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(" ")
+
+  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
+
+  # generator = torch.Generator('cuda').manual_seed(seed) if seed != 0 else None
+  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_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):
+
+    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
+
+        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)
+              )
+        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"
+
+    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):
+
+    print(f"{datetime.datetime.now()} img_to_img, model: {model_path}")
+
+    global last_mode
+    global pipe
+    global current_model_path
+    if model_path != current_model_path or last_mode != "img2img":
+        current_model_path = model_path
+
+        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"
+
+    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,
+        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}")
+        
+    return replace_nsfw_images(result)
+
+def replace_nsfw_images(results):
+
+    if is_colab:
+      return results.images
+      
+    for i in range(len(results.images)):
+      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 "")}
+              </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>
+            </div>
+        """
+    )
+    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.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)
+
+    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]
+    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[1].name, "Johnny Deep with red hair", 7.0, 35],
+        [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("""
+    <div style="border-top: 1px solid #303030;">
+      <br>
+      <p>Models by <a href="https://huggingface.co/darkstorm2150">@darkstorm2150</a> and others. ❤️</p>
+      <p>This space uses the <a href="https://github.com/LuChengTHU/dpm-solver">DPM-Solver++</a> sampler by <a href="https://arxiv.org/abs/2206.00927">Cheng Lu, et al.</a>.</p>
+      <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)

requirements.txt

@@ -0,0 +1,16 @@
+--extra-index-url https://download.pytorch.org/whl/cu113
+torch
+torchvision==0.13.1+cu113
+#diffusers
+git+https://github.com/huggingface/diffusers.git
+#transformers
+git+https://github.com/huggingface/transformers
+scipy
+ftfy
+psutil
+accelerate==0.12.0
+#OmegaConf
+#pytorch_lightning
+triton==2.0.0.dev20220701
+#https://github.com/apolinario/xformers/releases/download/0.0.3/xformers-0.0.14.dev0-cp38-cp38-linux_x86_64.whl
+https://github.com/camenduru/stable-diffusion-webui-colab/releases/download/0.0.15/xformers-0.0.15.dev0+4c06c79.d20221205-cp38-cp38-linux_x86_64.whl

style.css

@@ -0,0 +1,24 @@
+.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
+}

utils.py

@@ -0,0 +1,6 @@
+def is_google_colab():
+    try:
+        import google.colab
+        return True
+    except:
+        return False