Duplicate from LuChengTHU/dpmsolver_sdm

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

.gitattributes

@@ -0,0 +1,34 @@
+*.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
+*.ckpt 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 +1,13 @@
+---
+title: Dpmsolver Sdm
+emoji: 💻
+colorFrom: gray
+colorTo: red
+sdk: gradio
+sdk_version: 3.9
+app_file: app.py
+pinned: false
+duplicated_from: LuChengTHU/dpmsolver_sdm
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,276 @@
+from diffusers import AutoencoderKL, UNet2DConditionModel, StableDiffusionPipeline, StableDiffusionImg2ImgPipeline, DPMSolverMultistepScheduler
+import gradio as gr
+import torch
+from PIL import Image
+import os
+
+scheduler = DPMSolverMultistepScheduler(
+    beta_start=0.00085,
+    beta_end=0.012,
+    beta_schedule="scaled_linear",
+    num_train_timesteps=1000,
+    trained_betas=None,
+    predict_epsilon=True,
+    thresholding=False,
+    algorithm_type="dpmsolver++",
+    solver_type="midpoint",
+    lower_order_final=True,
+)
+
+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("Stable-Diffusion-v1.4", "CompVis/stable-diffusion-v1-4", "The 1.4 version of official stable-diffusion"),
+     Model("Waifu", "hakurei/waifu-diffusion", "anime style"),
+]
+
+last_mode = "txt2img"
+current_model = models[0]
+current_model_path = current_model.path
+
+auth_token = os.getenv("HUGGING_FACE_HUB_TOKEN")
+
+print(f"Is CUDA available: {torch.cuda.is_available()}")
+
+if torch.cuda.is_available():
+  vae = AutoencoderKL.from_pretrained(current_model.path, subfolder="vae", torch_dtype=torch.float16, use_auth_token=auth_token)
+  for model in models:
+    try:
+        unet = UNet2DConditionModel.from_pretrained(model.path, subfolder="unet", torch_dtype=torch.float16, use_auth_token=auth_token)
+        model.pipe_t2i = StableDiffusionPipeline.from_pretrained(model.path, unet=unet, vae=vae, torch_dtype=torch.float16, scheduler=scheduler, use_auth_token=auth_token)
+        model.pipe_i2i = StableDiffusionImg2ImgPipeline.from_pretrained(model.path, unet=unet, vae=vae, torch_dtype=torch.float16, scheduler=scheduler, use_auth_token=auth_token)
+    except:
+        models.remove(model)
+  pipe = models[0].pipe_t2i
+  pipe = pipe.to("cuda")
+
+else:
+  vae = AutoencoderKL.from_pretrained(current_model.path, subfolder="vae", use_auth_token=auth_token)
+  for model in models:
+    try:
+        unet = UNet2DConditionModel.from_pretrained(model.path, subfolder="unet", use_auth_token=auth_token)
+        model.pipe_t2i = StableDiffusionPipeline.from_pretrained(model.path, unet=unet, vae=vae, scheduler=scheduler, use_auth_token=auth_token)
+        model.pipe_i2i = StableDiffusionImg2ImgPipeline.from_pretrained(model.path, unet=unet, vae=vae, scheduler=scheduler, use_auth_token=auth_token)
+    except:
+        models.remove(model)
+  pipe = models[0].pipe_t2i
+  pipe = pipe.to("cpu")
+
+device = "GPU 🔥" if torch.cuda.is_available() else "CPU 🥶"
+
+def inference(model_name, prompt, guidance, steps, width=512, height=512, seed=0, img=None, strength=0.5, neg_prompt=""):
+
+  global current_model
+  for model in models:
+    if model.name == model_name:
+      current_model = model
+      model_path = current_model.path
+
+  generator = torch.Generator('cuda' if torch.cuda.is_available() else 'cpu').manual_seed(seed) if seed != 0 else None
+
+  if img is not None:
+    return img_to_img(model_path, prompt, neg_prompt, img, strength, guidance, steps, width, height, generator)
+  else:
+    return txt_to_img(model_path, prompt, neg_prompt, guidance, steps, width, height, generator)
+
+def txt_to_img(model_path, prompt, neg_prompt, guidance, steps, width, height, generator=None):
+
+    global last_mode
+    global pipe
+    global current_model_path
+    if model_path != current_model_path or last_mode != "txt2img":
+        current_model_path = model_path
+
+        pipe.to("cpu")
+        pipe = current_model.pipe_t2i
+
+        if torch.cuda.is_available():
+          pipe = pipe.to("cuda")
+        last_mode = "txt2img"
+
+    prompt = current_model.prefix + prompt
+    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)
+    
+    return replace_nsfw_images(result)
+
+def img_to_img(model_path, prompt, neg_prompt, img, strength, guidance, steps, width, height, generator=None):
+
+    global last_mode
+    global pipe
+    global current_model_path
+    if model_path != current_model_path or last_mode != "img2img":
+        current_model_path = model_path
+
+        pipe.to("cpu")
+        pipe = current_model.pipe_i2i
+        
+        if torch.cuda.is_available():
+          pipe = pipe.to("cuda")
+        last_mode = "img2img"
+
+    prompt = 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)
+    result = 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 replace_nsfw_images(result)
+
+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")
+    return results.images[0]
+
+css = """
+  <style>
+  .finetuned-diffusion-div {
+      text-align: center;
+      max-width: 700px;
+      margin: 0 auto;
+      font-family: 'IBM Plex Sans', sans-serif;
+    }
+    .finetuned-diffusion-div div {
+      display: inline-flex;
+      align-items: center;
+      gap: 0.8rem;
+      font-size: 1.75rem;
+    }
+    .finetuned-diffusion-div div h1 {
+      font-weight: 900;
+      margin-top: 15px;
+      margin-bottom: 15px;
+      text-align: center;
+    }
+    .finetuned-diffusion-div p {
+      margin-bottom: 10px;
+      font-size: 94%;
+    }
+    .finetuned-diffusion-div p a {
+      text-decoration: underline;
+    }
+    .tabs {
+      margin-top: 0px;
+      margin-bottom: 0px;
+    }
+    #gallery {
+      min-height: 20rem;
+    }
+    .container {
+      max-width: 1000px;
+      margin: auto;
+      padding-top: 1.5rem;
+    }
+  </style>
+"""
+with gr.Blocks(css=css) as demo:
+    gr.HTML(
+        f"""
+            <div class="finetuned-diffusion-div">
+              <div>
+                <h1>Stable-Diffusion with DPM-Solver (fastest sampler for diffusion models) </h1>
+              </div>
+              <br>
+              <p>
+              ❤️ Acknowledgement: Hardware resources of this demo are supported by HuggingFace 🤗 . Many thanks for the help!
+              </p>
+              <br>
+              <p>
+               This is a demo of sampling by DPM-Solver with two variants of Stable Diffusion models, including <a href="https://huggingface.co/CompVis/stable-diffusion-v1-4">Stable-Diffusion-v1.4</a> and <a href="https://huggingface.co/hakurei/waifu-diffusion">Waifu</a>.
+              </p>
+              <br>
+              <p>
+               <a href="https://github.com/LuChengTHU/dpm-solver">DPM-Solver</a> (Neurips 2022 Oral) is a fast high-order solver customized for diffusion ODEs, which can generate high-quality samples by diffusion models within only 10-25 steps. DPM-Solver has an analytical formulation and is very easy to use for all types of Gaussian diffusion models, and includes <a href="https://arxiv.org/abs/2010.02502">DDIM</a> as a first-order special case.
+              </p>
+              <p>
+              We use <a href="https://github.com/huggingface/diffusers">Diffusers</a>  🧨  to implement this demo, which currently supports the multistep DPM-Solver scheduler. For more details of DPM-Solver with Diffusers, check <a href="https://github.com/huggingface/diffusers/pull/1132">this pull request</a>.
+              </p>
+              <br>
+              <p>
+              Currently, the default sampler of stable-diffusion is <a href="https://arxiv.org/abs/2202.09778">PNDM</a>, which needs 50 steps to generate high-quality samples. However, DPM-Solver can generate high-quality samples within only <span style="font-weight: bold;">20-25</span> steps, and for some samples even within <span style="font-weight: bold;">10-15</span> steps.
+              </p>
+              <br>
+              <p>
+               Running on <b>{device}</b>
+              </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.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")
+
+        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=25, minimum=2, maximum=100, 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)
+
+    # model_name.change(lambda x: gr.update(visible = x == models[0].name), inputs=model_name, outputs=custom_model_group)
+
+    inputs = [model_name, prompt, guidance, steps, width, height, seed, image, strength, neg_prompt]
+    prompt.submit(inference, inputs=inputs, outputs=image_out)
+
+    generate.click(inference, inputs=inputs, outputs=image_out)
+
+
+    gr.Markdown('''
+      Stable-diffusion Models by [CompVis](https://huggingface.co/CompVis) and [stabilityai](https://huggingface.co/stabilityai), Waifu-diffusion models by [@hakurei](https://huggingface.co/hakurei). Most of the code of this demo are copied from [@anzorq's fintuned-diffusion](https://huggingface.co/spaces/anzorq/finetuned_diffusion/tree/main) ❤️<br>
+      Space by [Cheng Lu](https://github.com/LuChengTHU). [![Twitter Follow](https://img.shields.io/twitter/follow/ChengLu05671218?label=%40ChengLu&style=social)](https://twitter.com/ChengLu05671218)
+        
+      ![visitors](https://visitor-badge.glitch.me/badge?page_id=LuChengTHU.dpmsolver_sdm)
+    ''')
+
+demo.queue(concurrency_count=1)
+demo.launch(debug=False, share=False)

requirements.txt

@@ -0,0 +1,6 @@
+torch
+git+https://github.com/huggingface/diffusers.git
+transformers
+scipy
+ftfy
+accelerate