ValueError：输入格式不正确

Question

在运行 StableDiffusionInpaintPipeline 执行修复任务时，我遇到了一个持续存在的问题。尽管以预期的格式传递输入（图像和蒙版均采用 PIL.Image.Image 格式且大小正确），但我仍然收到以下错误：

ValueError: Input is in incorrect format. Currently, we only support <class 'PIL.Image.Image'>, <class 'numpy.ndarray'>, <class 'torch.Tensor'>

这是代码：

@torch.inference_mode()
def generate_image_bytes(base64_img, request, prompt) -> dict:
    # Get a model from the pool
    model = model_pool.get_model()
    
    try:
        if base64_img is not None:
            img_data = base64.b64decode(base64_img)
            img = Image.open(io.BytesIO(img_data))

            print("Recieved image of size: ", img.size)
        
        img = img.convert("RGB")
        image_np = np.array(img)
        
        roi_points = [
            request["box"]["x1"],
            request["box"]["y1"],
            request["box"]["x2"],
            request["box"]["y2"],
        ]

        results = model["seg_model"](
            image_np, 
            device="cuda", 
            conf=0.6, 
            iou=0.9, 
            bboxes = roi_points,
            labels=[1],
            verbose=False    
        )
        black_mask = np.zeros_like(image_np[:, :, 0], dtype=np.uint8)
        for m in results[0].masks.data:
            mask = m.cpu().numpy().astype(np.uint8)

            orig_shape = results[0].masks.orig_shape
            resized_mask = cv2.resize(mask, (orig_shape[1], orig_shape[0]))

            black_mask[resized_mask == 1] = 255
        
        image_pil = Image.fromarray(image_np)
        mask_pil = Image.fromarray(black_mask).convert("L")

        print(f"Image size: {image_pil.size}, mode: {image_pil.mode}")
        print(f"Mask size: {mask_pil.size}, mode: {mask_pil.mode}")
        
        generator = torch.Generator(device="cuda").manual_seed(0)

        image = model["pipeline"](
            prompt=prompt,
            negative_prompt=IMG_INPAINTING_NEG_PROMPT,
            image=image_pil,
            mask=mask_pil,
            guidance_scale=8.0,
            num_inference_steps=50,
            strength=0.05,
            generator=generator,
        ).images[0]

        # Convert image to bytes
        bytes = io.BytesIO()
        image.save(bytes, format="PNG")

        return {"bytes": base64.b64encode(bytes.getvalue()).decode("utf-8")}

我尝试查看这两个图像，即 image_pil 和 mask_pil，它们没有问题。它们的格式和大小也相同，但我仍然收到此错误。

Answer 1

好吧，它已经修好了，我必须通过

mask_image=mask_pil

，但我正在通过

mask=mask_pil