Update app.py

app.py

@@ -1,3 +1,213 @@
+import tempfile
+import time
+from collections.abc import Sequence
+from typing import Any, cast
+import os
+from huggingface_hub import login, hf_hub_download
+
+import gradio as gr
+import numpy as np
+import pillow_heif
+import spaces
+import torch
+from gradio_image_annotation import image_annotator
+from gradio_imageslider import ImageSlider
+from PIL import Image
+from pymatting.foreground.estimate_foreground_ml import estimate_foreground_ml
+from refiners.fluxion.utils import no_grad
+from refiners.solutions import BoxSegmenter
+from transformers import GroundingDinoForObjectDetection, GroundingDinoProcessor
+from diffusers import FluxPipeline
+
+BoundingBox = tuple[int, int, int, int]
+
+pillow_heif.register_heif_opener()
+pillow_heif.register_avif_opener()
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+# HF 토큰 설정
+HF_TOKEN = os.getenv("HF_TOKEN")
+if HF_TOKEN is None:
+    raise ValueError("Please set the HF_TOKEN environment variable")
+
+try:
+    login(token=HF_TOKEN)
+except Exception as e:
+    raise ValueError(f"Failed to login to Hugging Face: {str(e)}")
+
+# 모델 초기화
+segmenter = BoxSegmenter(device="cpu")
+segmenter.device = device
+segmenter.model = segmenter.model.to(device=segmenter.device)
+
+gd_model_path = "IDEA-Research/grounding-dino-base"
+gd_processor = GroundingDinoProcessor.from_pretrained(gd_model_path)
+gd_model = GroundingDinoForObjectDetection.from_pretrained(gd_model_path, torch_dtype=torch.float32)
+gd_model = gd_model.to(device=device)
+assert isinstance(gd_model, GroundingDinoForObjectDetection)
+
+# FLUX 파이프라인 초기화
+pipe = FluxPipeline.from_pretrained(
+    "black-forest-labs/FLUX.1-dev",
+    torch_dtype=torch.bfloat16,
+    use_auth_token=HF_TOKEN
+)
+pipe.load_lora_weights(
+    hf_hub_download(
+        "ByteDance/Hyper-SD",
+        "Hyper-FLUX.1-dev-8steps-lora.safetensors",
+        use_auth_token=HF_TOKEN
+    )
+)
+pipe.fuse_lora(lora_scale=0.125)
+pipe.to(device="cuda", dtype=torch.bfloat16)
+
+class timer:
+    def __init__(self, method_name="timed process"):
+        self.method = method_name
+    def __enter__(self):
+        self.start = time.time()
+        print(f"{self.method} starts")
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        end = time.time()
+        print(f"{self.method} took {str(round(end - self.start, 2))}s")
+
+def bbox_union(bboxes: Sequence[list[int]]) -> BoundingBox | None:
+    if not bboxes:
+        return None
+    for bbox in bboxes:
+        assert len(bbox) == 4
+        assert all(isinstance(x, int) for x in bbox)
+    return (
+        min(bbox[0] for bbox in bboxes),
+        min(bbox[1] for bbox in bboxes),
+        max(bbox[2] for bbox in bboxes),
+        max(bbox[3] for bbox in bboxes),
+    )
+
+def corners_to_pixels_format(bboxes: torch.Tensor, width: int, height: int) -> torch.Tensor:
+    x1, y1, x2, y2 = bboxes.round().to(torch.int32).unbind(-1)
+    return torch.stack((x1.clamp_(0, width), y1.clamp_(0, height), x2.clamp_(0, width), y2.clamp_(0, height)), dim=-1)
+
+def gd_detect(img: Image.Image, prompt: str) -> BoundingBox | None:
+    inputs = gd_processor(images=img, text=f"{prompt}.", return_tensors="pt").to(device=device)
+    with no_grad():
+        outputs = gd_model(**inputs)
+    width, height = img.size
+    results: dict[str, Any] = gd_processor.post_process_grounded_object_detection(
+        outputs,
+        inputs["input_ids"],
+        target_sizes=[(height, width)],
+    )[0]
+    assert "boxes" in results and isinstance(results["boxes"], torch.Tensor)
+    bboxes = corners_to_pixels_format(results["boxes"].cpu(), width, height)
+    return bbox_union(bboxes.numpy().tolist())
+
+def apply_mask(img: Image.Image, mask_img: Image.Image, defringe: bool = True) -> Image.Image:
+    assert img.size == mask_img.size
+    img = img.convert("RGB")
+    mask_img = mask_img.convert("L")
+    if defringe:
+        rgb, alpha = np.asarray(img) / 255.0, np.asarray(mask_img) / 255.0
+        foreground = cast(np.ndarray[Any, np.dtype[np.uint8]], estimate_foreground_ml(rgb, alpha))
+        img = Image.fromarray((foreground * 255).astype("uint8"))
+    result = Image.new("RGBA", img.size)
+    result.paste(img, (0, 0), mask_img)
+    return result
+
+def generate_background(prompt: str, width: int, height: int) -> Image.Image:
+    """배경 이미지 생성 함수"""
+    try:
+        with timer("Background generation"):
+            image = pipe(
+                prompt=prompt,
+                width=width,
+                height=height,
+                num_inference_steps=8,
+                guidance_scale=4.0,
+            ).images[0]
+        return image
+    except Exception as e:
+        raise gr.Error(f"Background generation failed: {str(e)}")
+
+def combine_with_background(foreground: Image.Image, background: Image.Image) -> Image.Image:
+    """전경과 배경 합성 함수"""
+    background = background.resize(foreground.size)
+    return Image.alpha_composite(background.convert('RGBA'), foreground)
+
+@spaces.GPU
+def _gpu_process(img: Image.Image, prompt: str | BoundingBox | None) -> tuple[Image.Image, BoundingBox | None, list[str]]:
+    time_log: list[str] = []
+    if isinstance(prompt, str):
+        t0 = time.time()
+        bbox = gd_detect(img, prompt)
+        time_log.append(f"detect: {time.time() - t0}")
+        if not bbox:
+            print(time_log[0])
+            raise gr.Error("No object detected")
+    else:
+        bbox = prompt
+    t0 = time.time()
+    mask = segmenter(img, bbox)
+    time_log.append(f"segment: {time.time() - t0}")
+    return mask, bbox, time_log
+
+def _process(img: Image.Image, prompt: str | BoundingBox | None, bg_prompt: str | None = None) -> tuple[tuple[Image.Image, Image.Image, Image.Image], gr.DownloadButton]:
+    if img.width > 2048 or img.height > 2048:
+        orig_res = max(img.width, img.height)
+        img.thumbnail((2048, 2048))
+        if isinstance(prompt, tuple):
+            x0, y0, x1, y1 = (int(x * 2048 / orig_res) for x in prompt)
+            prompt = (x0, y0, x1, y1)
+
+    mask, bbox, time_log = _gpu_process(img, prompt)
+    masked_alpha = apply_mask(img, mask, defringe=True)
+
+    if bg_prompt:
+        try:
+            background = generate_background(bg_prompt, img.width, img.height)
+            combined = combine_with_background(masked_alpha, background)
+        except Exception as e:
+            raise gr.Error(f"Background processing failed: {str(e)}")
+    else:
+        combined = Image.alpha_composite(Image.new("RGBA", masked_alpha.size, "white"), masked_alpha)
+
+    thresholded = mask.point(lambda p: 255 if p > 10 else 0)
+    bbox = thresholded.getbbox()
+    to_dl = masked_alpha.crop(bbox)
+
+    temp = tempfile.NamedTemporaryFile(delete=False, suffix=".png")
+    to_dl.save(temp, format="PNG")
+    temp.close()
+
+    return (img, combined, masked_alpha), gr.DownloadButton(value=temp.name, interactive=True)
+
+def process_bbox(prompts: dict[str, Any]) -> tuple[tuple[Image.Image, Image.Image], gr.DownloadButton]:
+    assert isinstance(img := prompts["image"], Image.Image)
+    assert isinstance(boxes := prompts["boxes"], list)
+    if len(boxes) == 1:
+        assert isinstance(box := boxes[0], dict)
+        bbox = tuple(box[k] for k in ["xmin", "ymin", "xmax", "ymax"])
+    else:
+        assert len(boxes) == 0
+        bbox = None
+    return _process(img, bbox)
+
+def on_change_bbox(prompts: dict[str, Any] | None):
+    return gr.update(interactive=prompts is not None)
+
+def process_prompt(img: Image.Image, prompt: str, bg_prompt: str | None = None) -> tuple[tuple[Image.Image, Image.Image], gr.DownloadButton]:
+    return _process(img, prompt, bg_prompt)
+
+def on_change_prompt(img: Image.Image | None, prompt: str | None, bg_prompt: str | None = None):
+    return gr.update(interactive=bool(img and prompt))
+
+def update_button_state(img, prompt):
+    return gr.Button.update(interactive=bool(img and prompt))
+
+
+
 # Gradio UI 부분 수정
 with gr.Blocks(theme=gr.themes.Soft(), css=css) as demo:
     gr.HTML("""