Inpainting

.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

README.md

@@ -0,0 +1,12 @@
+---
+title: Image To Image
+emoji: 📊
+colorFrom: gray
+colorTo: pink
+sdk: gradio
+sdk_version: 4.44.0
+app_file: app.py
+pinned: false
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,152 @@
+import os
+
+import gradio as gr
+import spaces
+import torch
+from diffusers import AutoPipelineForInpainting
+from loguru import logger
+from PIL import Image
+
+SUPPORTED_MODELS = [
+    "stabilityai/sdxl-turbo",
+    "stabilityai/stable-diffusion-3-medium-diffusers",
+    "stabilityai/stable-diffusion-xl-base-1.0",
+    "timbrooks/instruct-pix2pix",
+]
+DEFAULT_MODEL = "stabilityai/stable-diffusion-xl-base-1.0"
+
+
+model = os.environ.get("MODEL_ID", DEFAULT_MODEL)
+gpu_duration = int(os.environ.get("GPU_DURATION", 60))
+
+
+def load_pipeline(model):
+    return AutoPipelineForInpainting.from_pretrained(
+        model, torch_dtype=torch.float16, use_safetensors=True, variant="fp16"
+    )
+
+
+logger.debug(f"Loading pipeline: {dict(model=model)}")
+pipe = load_pipeline(model).to("cuda")
+
+
+@logger.catch(reraise=True)
+@spaces.GPU(duration=gpu_duration)
+def infer(
+    prompt: str,
+    image_editor: dict,
+    negative_prompt: str,
+    strength: float,
+    num_inference_steps: int,
+    guidance_scale: float,
+    progress=gr.Progress(track_tqdm=True),
+):
+    logger.info(
+        f"Starting image generation: {dict(model=model, prompt=prompt, image_editor=image_editor)}"
+    )
+
+    init_image: Image.Image = image_editor["background"].convert("RGB")
+    mask_image: Image.Image = image_editor["composite"].convert("RGB")
+
+    # Downscale the image
+    init_image.thumbnail((1024, 1024))
+    mask_image.thumbnail((1024, 1024))
+
+    additional_args = {
+        k: v
+        for k, v in dict(
+            strength=strength,
+            num_inference_steps=num_inference_steps,
+            guidance_scale=guidance_scale,
+        ).items()
+        if v
+    }
+
+    logger.debug(f"Generating image: {dict(prompt=prompt, **additional_args)}")
+
+    images = pipe(
+        prompt=prompt,
+        image=init_image,
+        mask_image=mask_image,
+        negative_prompt=negative_prompt,
+        **additional_args,
+    ).images
+    return images[0]
+
+
+css = """
+@media (max-width: 1280px) {
+  #images-container {
+    flex-direction: column;
+  }
+}
+"""
+
+with gr.Blocks(css=css) as demo:
+    with gr.Column():
+        gr.Markdown("# Inpainting")
+        gr.Markdown(f"## Model: `{model}`")
+
+        with gr.Row():
+            prompt = gr.Text(
+                label="Prompt",
+                show_label=False,
+                max_lines=1,
+                placeholder="Enter your prompt",
+                container=False,
+            )
+
+            run_button = gr.Button("Run", scale=0, variant="primary")
+
+        with gr.Row(elem_id="images-container"):
+            image_editor = gr.ImageMask(label="Initial image", type="pil")
+
+            result = gr.Image(label="Result")
+
+        with gr.Accordion("Advanced Settings", open=False):
+            negative_prompt = gr.Text(
+                label="Negative prompt",
+                max_lines=1,
+                placeholder="Enter a negative prompt",
+            )
+
+            with gr.Row():
+                strength = gr.Slider(
+                    label="Strength",
+                    minimum=0.0,
+                    maximum=1.0,
+                    step=0.01,
+                    value=0.0,
+                )
+
+                num_inference_steps = gr.Slider(
+                    label="Number of inference steps",
+                    minimum=0,
+                    maximum=100,
+                    step=1,
+                    value=0,
+                )
+
+                guidance_scale = gr.Slider(
+                    label="Guidance scale",
+                    minimum=0.0,
+                    maximum=100.0,
+                    step=0.1,
+                    value=0.0,
+                )
+    gr.on(
+        triggers=[run_button.click, prompt.submit],
+        fn=infer,
+        inputs=[
+            prompt,
+            image_editor,
+            negative_prompt,
+            strength,
+            num_inference_steps,
+            guidance_scale,
+        ],
+        outputs=[result],
+    )
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,6 @@
+accelerate
+diffusers
+loguru
+sentencepiece
+torch
+transformers