Duplicate from nitrosocke/Diffusion_Space

Co-authored-by: Nitrosocke <[email protected]>

.gitattributes

@@ -0,0 +1,33 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+---
+title: Diffusion Space
+emoji: 💽
+colorFrom: blue
+colorTo: pink
+sdk: gradio
+sdk_version: 3.6
+app_file: app.py
+pinned: true
+license: creativeml-openrail-m
+duplicated_from: nitrosocke/Diffusion_Space
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,279 @@
+import gradio as gr
+import cv2
+import torch
+import utils
+import datetime
+import time
+import psutil
+from imwatermark import WatermarkEncoder
+import numpy as np
+from PIL import Image
+from diffusers import EulerAncestralDiscreteScheduler, EulerDiscreteScheduler, AutoencoderKL, UNet2DConditionModel, StableDiffusionPipeline, StableDiffusionImg2ImgPipeline
+
+start_time = time.time()
+is_colab = utils.is_google_colab()
+
+#wm = "SDV2"
+#wm_encoder = WatermarkEncoder()
+#wm_encoder.set_watermark('bytes', wm.encode('utf-8'))
+#def put_watermark(img, wm_encoder=None):
+#    if wm_encoder is not None:
+#        img = cv2.cvtColor(np.array(img), cv2.COLOR_RGB2BGR)
+#        img = wm_encoder.encode(img, 'dwtDct')
+#        img = Image.fromarray(img[:, :, ::-1])
+#    return img
+
+class Model:
+    def __init__(self, name, path="", prefix=""):
+        self.name = name
+        self.path = path
+        self.prefix = prefix
+        self.pipe_t2i = None
+        self.pipe_i2i = None
+
+models = [
+   Model("Redshift Diffusion 768", "nitrosocke/redshift-diffusion-768", "redshift style")
+  ]
+    #  Model("Ghibli Diffusion", "nitrosocke/Ghibli-Diffusion", "ghibli style"),
+    #  Model("Redshift Diffusion", "nitrosocke/Redshift-Diffusion", "redshift style"),
+    #  Model("Nitro Diffusion", "nitrosocke/Nitro-Diffusion", "archer arcane modern disney"),
+
+scheduler = EulerDiscreteScheduler.from_pretrained("stabilityai/stable-diffusion-2", subfolder="scheduler", prediction_type="v_prediction")
+
+#scheduler = EulerDiscreteScheduler.from_pretrained("stabilityai/stable-diffusion-2-base", subfolder="scheduler")
+
+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=scheduler)
+
+else: # download all models
+  print(f"{datetime.datetime.now()} Downloading vae...")
+  pipe = StableDiffusionPipeline.from_pretrained(current_model_path, torch_dtype=torch.float16, scheduler=scheduler)
+  #vae = AutoencoderKL.from_pretrained(current_model.path, subfolder="vae", torch_dtype=torch.float16)
+  for model in models:
+    try:
+        print(f"{datetime.datetime.now()} Downloading {model.name} model...")
+        unet = UNet2DConditionModel.from_pretrained(model.path, subfolder="unet", torch_dtype=torch.float16)
+        model.pipe_t2i = StableDiffusionPipeline.from_pretrained(model.path, unet=unet, torch_dtype=torch.float16, scheduler=scheduler)
+        model.pipe_i2i = StableDiffusionImg2ImgPipeline.from_pretrained(model.path, unet=unet, torch_dtype=torch.float16, scheduler=scheduler)
+    except Exception as e:
+        print(f"{datetime.datetime.now()} Failed to load model " + model.name + ": " + str(e))
+        models.remove(model)
+  pipe = models[0].pipe_t2i
+  
+if torch.cuda.is_available():
+  pipe = pipe.to("cuda")
+
+device = "GPU 🔥" if torch.cuda.is_available() else "CPU 🥶"
+
+def error_str(error, title="Error"):
+    return f"""#### {title}
+            {error}"""  if error else ""
+
+def custom_model_changed(path):
+  models[0].path = path
+  global current_model
+  current_model = models[0]
+
+def on_model_change(model_name):
+  
+  prefix = "Enter prompt. \"" + next((m.prefix for m in models if m.name == model_name), None) + "\" is prefixed automatically" if model_name != models[0].name else "Don't forget to use the custom model prefix in the prompt!"
+
+  return gr.update(visible = model_name == models[0].name), gr.update(placeholder=prefix)
+
+def inference(model_name, prompt, guidance, steps, width=512, height=512, seed=0, img=None, strength=0.5, neg_prompt=""):
+
+  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
+
+  try:
+    if img is not None:
+      return img_to_img(model_path, prompt, neg_prompt, img, strength, guidance, steps, width, height, generator), None
+    else:
+      return txt_to_img(model_path, prompt, neg_prompt, guidance, steps, width, height, generator), None
+  except Exception as e:
+    return None, error_str(e)
+
+def txt_to_img(model_path, prompt, neg_prompt, guidance, steps, width, height, generator):
+
+    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
+
+        if is_colab or current_model == custom_model:
+          pipe = StableDiffusionPipeline.from_pretrained(current_model_path, torch_dtype=torch.float16, scheduler=scheduler)
+        else:
+          pipe = pipe.to("cpu")
+          pipe = current_model.pipe_t2i
+
+        if torch.cuda.is_available():
+          pipe = pipe.to("cuda")
+        last_mode = "txt2img"
+
+    prompt = f"{current_model.prefix} {prompt}"  
+    results = 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)
+    
+    return results.images[0]
+
+def img_to_img(model_path, prompt, neg_prompt, img, strength, guidance, steps, width, height, generator):
+
+    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
+
+        if is_colab or current_model == custom_model:
+          pipe = StableDiffusionPipeline.from_pretrained(current_model_path, torch_dtype=torch.float16, scheduler=scheduler)
+        else:
+          pipe = pipe.to("cpu")
+          pipe = current_model.pipe_i2i
+        
+        if torch.cuda.is_available():
+          pipe = pipe.to("cuda")
+        last_mode = "img2img"
+
+    prompt = f"{current_model.prefix} {prompt}"
+    ratio = min(height / img.height, width / img.width)
+    img = img.resize((int(img.width * ratio), int(img.height * ratio)), Image.LANCZOS)
+    results = pipe(
+        prompt,
+        negative_prompt = neg_prompt,
+        # num_images_per_prompt=n_images,
+        init_image = img,
+        num_inference_steps = int(steps),
+        strength = strength,
+        guidance_scale = guidance,
+        width = width,
+        height = height,
+        generator = generator)
+        
+    return results.images[0]
+
+def replace_nsfw_images(results):
+
+    if is_colab:
+      return results.images[0]
+      
+    for i in range(len(results.images)):
+      if results.nsfw_content_detected[i]:
+        results.images[i] = Image.open("nsfw.png")
+    return results.images[0]
+
+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=css) as demo:
+    gr.HTML(
+        f"""
+            <div class="diffusion-spave-div">
+              <div>
+                <h1>Diffusion Space</h1>
+              </div>
+              <p>
+               Demo for Nitrosocke's fine-tuned models.
+              </p>
+              <p>You can skip the queue and load custom models in the colab: <a href="https://colab.research.google.com/drive/1Yr2QvQcqLHlApoQHDPzZmKREizVm9iZw"><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>
+              <p>You can also duplicate this space and upgrade to gpu by going to settings: <a style="display:inline-block" href="https://huggingface.co/spaces/nitrosocke/Diffusion_Space?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>
+              </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="nitrosocke/Future-Diffusion", 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 applied automatically").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=[1], height="auto")
+          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, maximum=15, step=1)
+                steps = gr.Slider(label="Steps", value=20, minimum=2, maximum=30, step=1)
+
+              with gr.Row():
+                width = gr.Slider(label="Width", value=768, minimum=768, maximum=1024, step=64)
+                height = gr.Slider(label="Height", value=768, minimum=768, maximum=1024, step=64)
+
+              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)
+
+    inputs = [model_name, prompt, guidance, steps, width, height, seed, image, strength, neg_prompt]
+    outputs = [image_out, error_output]
+    prompt.submit(inference, inputs=inputs, outputs=outputs)
+    generate.click(inference, inputs=inputs, outputs=outputs)
+
+    ex = gr.Examples([
+       [models[0].name, "redshift style portrait black female cyberpunk hacker tattoos colorful short hair wearing a crop top redshift style", "mutated body double head bad anatomy long face long neck long body text watermark signature", 7, 20],
+       [models[0].name, "redshift style beautiful fjord at sunrise", "fog blurry soft", 7, 20],
+      
+    ], inputs=[model_name, prompt, neg_prompt, guidance, steps, seed], outputs=outputs, fn=inference, cache_examples=False)
+
+    gr.HTML("""
+    <div style="border-top: 1px solid #303030;">
+      <br>
+      <p>Model by Nitrosocke.</p>
+    </div>
+    """)
+
+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 +1,10 @@
+--extra-index-url https://download.pytorch.org/whl/cu113
+torch==1.13.0
+torchvision
+git+https://github.com/huggingface/diffusers.git
+transformers
+accelerate
+ftfy
+python-dotenv
+invisible-watermark
+https://github.com/apolinario/xformers/releases/download/0.0.3/xformers-0.0.14.dev0-cp38-cp38-linux_x86_64.whl

utils.py

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