Duplicate from TencentARC/T2I-Adapter-SDXL-Sketch

Co-authored-by: hysts <hysts@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,35 @@
+*.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
+*.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

.pre-commit-config.yaml

@@ -0,0 +1,50 @@
+repos:
+- repo: https://github.com/pre-commit/pre-commit-hooks
+  rev: v4.4.0
+  hooks:
+  - id: check-executables-have-shebangs
+  - id: check-json
+  - id: check-merge-conflict
+  - id: check-shebang-scripts-are-executable
+  - id: check-toml
+  - id: check-yaml
+  - id: end-of-file-fixer
+  - id: mixed-line-ending
+    args: ["--fix=lf"]
+  - id: requirements-txt-fixer
+  - id: trailing-whitespace
+- repo: https://github.com/myint/docformatter
+  rev: v1.7.5
+  hooks:
+  - id: docformatter
+    args: ["--in-place"]
+- repo: https://github.com/pycqa/isort
+  rev: 5.12.0
+  hooks:
+    - id: isort
+      args: ["--profile", "black"]
+- repo: https://github.com/pre-commit/mirrors-mypy
+  rev: v1.5.1
+  hooks:
+    - id: mypy
+      args: ["--ignore-missing-imports"]
+      additional_dependencies: ["types-python-slugify", "types-requests", "types-PyYAML"]
+- repo: https://github.com/psf/black
+  rev: 23.7.0
+  hooks:
+    - id: black
+      language_version: python3.10
+      args: ["--line-length", "119"]
+- repo: https://github.com/kynan/nbstripout
+  rev: 0.6.1
+  hooks:
+    - id: nbstripout
+      args: ["--extra-keys", "metadata.interpreter metadata.kernelspec cell.metadata.pycharm"]
+- repo: https://github.com/nbQA-dev/nbQA
+  rev: 1.7.0
+  hooks:
+    - id: nbqa-black
+    - id: nbqa-pyupgrade
+      args: ["--py37-plus"]
+    - id: nbqa-isort
+      args: ["--float-to-top"]

.vscode/settings.json

@@ -0,0 +1,21 @@
+{
+    "[python]": {
+        "editor.defaultFormatter": "ms-python.black-formatter",
+        "editor.formatOnType": true,
+        "editor.codeActionsOnSave": {
+            "source.organizeImports": true
+        }
+    },
+    "black-formatter.args": [
+        "--line-length=119"
+    ],
+    "isort.args": ["--profile", "black"],
+    "flake8.args": [
+        "--max-line-length=119"
+    ],
+    "ruff.args": [
+        "--line-length=119"
+    ],
+    "editor.formatOnSave": true,
+    "files.insertFinalNewline": true
+}

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 hysts
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -0,0 +1,13 @@
+---
+title: T2I Adapter SDXL Sketch
+emoji: 🚀
+colorFrom: blue
+colorTo: purple
+sdk: gradio
+sdk_version: 3.43.1
+app_file: app.py
+pinned: false
+duplicated_from: TencentARC/T2I-Adapter-SDXL-Sketch
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,266 @@
+#!/usr/bin/env python
+
+import os
+import random
+
+import gradio as gr
+import numpy as np
+import PIL.Image
+import torch
+import torchvision.transforms.functional as TF
+from diffusers import (
+    AutoencoderKL,
+    EulerAncestralDiscreteScheduler,
+    StableDiffusionXLAdapterPipeline,
+    T2IAdapter,
+)
+
+DESCRIPTION = '''# Doodly - T2I-Adapter-SDXL **Sketch**
+To try out all the [6 T2I-Adapter](https://huggingface.co/collections/TencentARC/t2i-adapter-sdxl-64fac9cbf393f30370eeb02f) released for SDXL, [click here](https://huggingface.co/spaces/TencentARC/T2I-Adapter-SDXL)
+'''
+
+if not torch.cuda.is_available():
+    DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>"
+
+style_list = [
+    {
+        "name": "(No style)",
+        "prompt": "{prompt}",
+        "negative_prompt": "",
+    },
+    {
+        "name": "Cinematic",
+        "prompt": "cinematic still {prompt} . emotional, harmonious, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy",
+        "negative_prompt": "anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured",
+    },
+    {
+        "name": "3D Model",
+        "prompt": "professional 3d model {prompt} . octane render, highly detailed, volumetric, dramatic lighting",
+        "negative_prompt": "ugly, deformed, noisy, low poly, blurry, painting",
+    },
+    {
+        "name": "Anime",
+        "prompt": "anime artwork {prompt} . anime style, key visual, vibrant, studio anime,  highly detailed",
+        "negative_prompt": "photo, deformed, black and white, realism, disfigured, low contrast",
+    },
+    {
+        "name": "Digital Art",
+        "prompt": "concept art {prompt} . digital artwork, illustrative, painterly, matte painting, highly detailed",
+        "negative_prompt": "photo, photorealistic, realism, ugly",
+    },
+    {
+        "name": "Photographic",
+        "prompt": "cinematic photo {prompt} . 35mm photograph, film, bokeh, professional, 4k, highly detailed",
+        "negative_prompt": "drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly",
+    },
+    {
+        "name": "Pixel art",
+        "prompt": "pixel-art {prompt} . low-res, blocky, pixel art style, 8-bit graphics",
+        "negative_prompt": "sloppy, messy, blurry, noisy, highly detailed, ultra textured, photo, realistic",
+    },
+    {
+        "name": "Fantasy art",
+        "prompt": "ethereal fantasy concept art of  {prompt} . magnificent, celestial, ethereal, painterly, epic, majestic, magical, fantasy art, cover art, dreamy",
+        "negative_prompt": "photographic, realistic, realism, 35mm film, dslr, cropped, frame, text, deformed, glitch, noise, noisy, off-center, deformed, cross-eyed, closed eyes, bad anatomy, ugly, disfigured, sloppy, duplicate, mutated, black and white",
+    },
+    {
+        "name": "Neonpunk",
+        "prompt": "neonpunk style {prompt} . cyberpunk, vaporwave, neon, vibes, vibrant, stunningly beautiful, crisp, detailed, sleek, ultramodern, magenta highlights, dark purple shadows, high contrast, cinematic, ultra detailed, intricate, professional",
+        "negative_prompt": "painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured",
+    },
+    {
+        "name": "Manga",
+        "prompt": "manga style {prompt} . vibrant, high-energy, detailed, iconic, Japanese comic style",
+        "negative_prompt": "ugly, deformed, noisy, blurry, low contrast, realism, photorealistic, Western comic style",
+    },
+]
+
+styles = {k["name"]: (k["prompt"], k["negative_prompt"]) for k in style_list}
+STYLE_NAMES = list(styles.keys())
+DEFAULT_STYLE_NAME = "(No style)"
+
+
+def apply_style(style_name: str, positive: str, negative: str = "") -> tuple[str, str]:
+    p, n = styles.get(style_name, styles[DEFAULT_STYLE_NAME])
+    return p.replace("{prompt}", positive), n + negative
+
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+if torch.cuda.is_available():
+    model_id = "stabilityai/stable-diffusion-xl-base-1.0"
+    adapter = T2IAdapter.from_pretrained(
+        "TencentARC/t2i-adapter-sketch-sdxl-1.0", torch_dtype=torch.float16, variant="fp16"
+    )
+    scheduler = EulerAncestralDiscreteScheduler.from_pretrained(model_id, subfolder="scheduler")
+    pipe = StableDiffusionXLAdapterPipeline.from_pretrained(
+        model_id,
+        vae=AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16),
+        adapter=adapter,
+        scheduler=scheduler,
+        torch_dtype=torch.float16,
+        variant="fp16",
+    )
+    pipe.to(device)
+else:
+    pipe = None
+
+MAX_SEED = np.iinfo(np.int32).max
+
+
+def randomize_seed_fn(seed: int, randomize_seed: bool) -> int:
+    if randomize_seed:
+        seed = random.randint(0, MAX_SEED)
+    return seed
+
+
+def run(
+    image: PIL.Image.Image,
+    prompt: str,
+    negative_prompt: str,
+    style_name: str = DEFAULT_STYLE_NAME,
+    num_steps: int = 25,
+    guidance_scale: float = 5,
+    adapter_conditioning_scale: float = 0.8,
+    adapter_conditioning_factor: float = 0.8,
+    seed: int = 0,
+    progress=gr.Progress(track_tqdm=True),
+) -> PIL.Image.Image:
+    image = image.convert("RGB")
+    image = TF.to_tensor(image) > 0.5
+    image = TF.to_pil_image(image.to(torch.float32))
+
+    prompt, negative_prompt = apply_style(style_name, prompt, negative_prompt)
+
+    generator = torch.Generator(device=device).manual_seed(seed)
+    out = pipe(
+        prompt=prompt,
+        negative_prompt=negative_prompt,
+        image=image,
+        num_inference_steps=num_steps,
+        generator=generator,
+        guidance_scale=guidance_scale,
+        adapter_conditioning_scale=adapter_conditioning_scale,
+        adapter_conditioning_factor=adapter_conditioning_factor,
+    ).images[0]
+    return out
+
+
+with gr.Blocks(css="style.css") as demo:
+    gr.Markdown(DESCRIPTION, elem_id="description")
+    gr.DuplicateButton(
+        value="Duplicate Space for private use",
+        elem_id="duplicate-button",
+        visible=os.getenv("SHOW_DUPLICATE_BUTTON") == "1",
+    )
+
+    with gr.Row():
+        with gr.Column():
+            with gr.Group():
+                image = gr.Image(
+                    source="canvas",
+                    tool="sketch",
+                    type="pil",
+                    image_mode="L",
+                    invert_colors=True,
+                    shape=(1024, 1024),
+                    brush_radius=4,
+                    height=440,
+                )
+                prompt = gr.Textbox(label="Prompt")
+                style = gr.Dropdown(label="Style", choices=STYLE_NAMES, value=DEFAULT_STYLE_NAME)
+                run_button = gr.Button("Run")
+            with gr.Accordion("Advanced options", open=False):
+                negative_prompt = gr.Textbox(
+                    label="Negative prompt",
+                    value=" extra digit, fewer digits, cropped, worst quality, low quality, glitch, deformed, mutated, ugly, disfigured",
+                )
+                num_steps = gr.Slider(
+                    label="Number of steps",
+                    minimum=1,
+                    maximum=50,
+                    step=1,
+                    value=25,
+                )
+                guidance_scale = gr.Slider(
+                    label="Guidance scale",
+                    minimum=0.1,
+                    maximum=10.0,
+                    step=0.1,
+                    value=5,
+                )
+                adapter_conditioning_scale = gr.Slider(
+                    label="Adapter conditioning scale",
+                    minimum=0.5,
+                    maximum=1,
+                    step=0.1,
+                    value=0.8,
+                )
+                adapter_conditioning_factor = gr.Slider(
+                    label="Adapter conditioning factor",
+                    info="Fraction of timesteps for which adapter should be applied",
+                    minimum=0.5,
+                    maximum=1,
+                    step=0.1,
+                    value=0.8,
+                )
+                seed = gr.Slider(
+                    label="Seed",
+                    minimum=0,
+                    maximum=MAX_SEED,
+                    step=1,
+                    value=0,
+                )
+                randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
+        with gr.Column():
+            result = gr.Image(label="Result", height=400)
+
+    inputs = [
+        image,
+        prompt,
+        negative_prompt,
+        style,
+        num_steps,
+        guidance_scale,
+        adapter_conditioning_scale,
+        adapter_conditioning_factor,
+        seed,
+    ]
+    prompt.submit(
+        fn=randomize_seed_fn,
+        inputs=[seed, randomize_seed],
+        outputs=seed,
+        queue=False,
+        api_name=False,
+    ).then(
+        fn=run,
+        inputs=inputs,
+        outputs=result,
+        api_name=False,
+    )
+    negative_prompt.submit(
+        fn=randomize_seed_fn,
+        inputs=[seed, randomize_seed],
+        outputs=seed,
+        queue=False,
+        api_name=False,
+    ).then(
+        fn=run,
+        inputs=inputs,
+        outputs=result,
+        api_name=False,
+    )
+    run_button.click(
+        fn=randomize_seed_fn,
+        inputs=[seed, randomize_seed],
+        outputs=seed,
+        queue=False,
+        api_name=False,
+    ).then(
+        fn=run,
+        inputs=inputs,
+        outputs=result,
+        api_name=False,
+    )
+
+if __name__ == "__main__":
+    demo.queue(max_size=20).launch()

requirements.txt

@@ -0,0 +1,9 @@
+accelerate==0.22.0
+git+https://github.com/huggingface/diffusers@t2i-adapter-load-lora
+gradio==3.43.1
+Pillow==10.0.0
+safetensors==0.3.3
+torch==2.0.1
+torchvision==0.15.2
+transformers==4.33.1
+xformers==0.0.20

style.css

@@ -0,0 +1,16 @@
+
+#component-0{
+  max-width: 900px;
+  margin: 0 auto;
+}
+
+#description, h1 {
+  text-align: center;
+}
+
+#duplicate-button {
+  margin: auto;
+  color: #fff;
+  background: #1565c0;
+  border-radius: 100vh;
+}