RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 96 but got size 768 for tensor number 2 in the list

🧨 Diffusers
1

why some image produce such error?

ERROR:    Exception in ASGI application
Traceback (most recent call last):
  File "/workspace/api101/venv/lib/python3.10/site-packages/uvicorn/protocols/http/httptools_impl.py", line 426, in run_asgi
    result = await app(  # type: ignore[func-returns-value]
  File "/workspace/api101/venv/lib/python3.10/site-packages/uvicorn/middleware/proxy_headers.py", line 84, in __call__
    return await self.app(scope, receive, send)
  File "/workspace/api101/venv/lib/python3.10/site-packages/fastapi/applications.py", line 292, in __call__
    await super().__call__(scope, receive, send)
  File "/workspace/api101/venv/lib/python3.10/site-packages/starlette/applications.py", line 122, in __call__
    await self.middleware_stack(scope, receive, send)
  File "/workspace/api101/venv/lib/python3.10/site-packages/starlette/middleware/errors.py", line 184, in __call__
    raise exc
  File "/workspace/api101/venv/lib/python3.10/site-packages/starlette/middleware/errors.py", line 162, in __call__
    await self.app(scope, receive, _send)
  File "/workspace/api101/venv/lib/python3.10/site-packages/starlette/middleware/cors.py", line 83, in __call__
    await self.app(scope, receive, send)
  File "/workspace/api101/venv/lib/python3.10/site-packages/starlette/middleware/exceptions.py", line 79, in __call__
    raise exc
  File "/workspace/api101/venv/lib/python3.10/site-packages/starlette/middleware/exceptions.py", line 68, in __call__
    await self.app(scope, receive, sender)
  File "/workspace/api101/venv/lib/python3.10/site-packages/fastapi/middleware/asyncexitstack.py", line 20, in __call__
    raise e
  File "/workspace/api101/venv/lib/python3.10/site-packages/fastapi/middleware/asyncexitstack.py", line 17, in __call__
    await self.app(scope, receive, send)
  File "/workspace/api101/venv/lib/python3.10/site-packages/starlette/routing.py", line 718, in __call__
    await route.handle(scope, receive, send)
  File "/workspace/api101/venv/lib/python3.10/site-packages/starlette/routing.py", line 276, in handle
    await self.app(scope, receive, send)
  File "/workspace/api101/venv/lib/python3.10/site-packages/starlette/routing.py", line 66, in app
    response = await func(request)
  File "/workspace/api101/venv/lib/python3.10/site-packages/fastapi/routing.py", line 273, in app
    raw_response = await run_endpoint_function(
  File "/workspace/api101/venv/lib/python3.10/site-packages/fastapi/routing.py", line 190, in run_endpoint_function
    return await dependant.call(**values)
  File "/workspace/api101/main.py", line 106, in replace_background
    output_image = pipe(
  File "/workspace/api101/venv/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "/workspace/api101/venv/lib/python3.10/site-packages/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_inpaint.py", line 982, in __call__
    latent_model_input = torch.cat([latent_model_input, mask, masked_image_latents], dim=1)
RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 96 but got size 768 for tensor number 2 in the list.

@app.post('/replace-background/')
async def replace_background (
    input: UploadFile = Form(),
    prompt: str = Form(),
    width: int = Form(),
    height: int = Form(),
    steps: Optional[int] = Form(20),
    strength: Optional[float] = Form(1.0),
    
    return_base64: Optional[bool] = Form(False)
):
    file = await input.read()
    
    image = Image.open(io.BytesIO(file))
    mask = rembg.remove(image, only_mask=True)


    init_image = image.resize(image.size)
    mask_image = ImageOps.invert(mask.resize(init_image.size))

    model = './realisticVisionV51_v51VAE-inpainting.safetensors'

    pipe = StableDiffusionInpaintPipeline.from_single_file(model).to('cuda')
    
    output_image = pipe(
        prompt = prompt,
        image = image,
        mask_image = mask,
        width = width,
        height = height,
        strength = strength,
        num_inference_steps = steps,
    ).images[0]

    buffer = io.BytesIO()

    output_image.resize((image.width, image.height)).save(buffer, 'PNG')
    
    buffer.seek(0)

    if return_base64:
        encoded_image = base64.b64encode(buffer.getvalue()).decode('utf-8')
        return { 'image_base64': encoded_image }
    else:
        return StreamingResponse(buffer, media_type = 'image/png')

this one failed

download (4)
download (4)512×768 51.1 KB