OpenAI DALL·E 2 - ComfyUI Native Node Documentation

class OpenAIDalle2(ComfyNodeABC):
    """
    Generates images synchronously via OpenAI's DALL·E 2 endpoint.

    Uses the proxy at /proxy/openai/images/generations. Returned URLs are short‑lived,
    so download or cache results if you need to keep them.
    """

    def __init__(self):
        pass

    @classmethod
    def INPUT_TYPES(cls) -> InputTypeDict:
        return {
            "required": {
                "prompt": (
                    IO.STRING,
                    {
                        "multiline": True,
                        "default": "",
                        "tooltip": "Text prompt for DALL·E",
                    },
                ),
            },
            "optional": {
                "seed": (
                    IO.INT,
                    {
                        "default": 0,
                        "min": 0,
                        "max": 2**31 - 1,
                        "step": 1,
                        "display": "number",
                        "control_after_generate": True,
                        "tooltip": "not implemented yet in backend",
                    },
                ),
                "size": (
                    IO.COMBO,
                    {
                        "options": ["256x256", "512x512", "1024x1024"],
                        "default": "1024x1024",
                        "tooltip": "Image size",
                    },
                ),
                "n": (
                    IO.INT,
                    {
                        "default": 1,
                        "min": 1,
                        "max": 8,
                        "step": 1,
                        "display": "number",
                        "tooltip": "How many images to generate",
                    },
                ),
                "image": (
                    IO.IMAGE,
                    {
                        "default": None,
                        "tooltip": "Optional reference image for image editing.",
                    },
                ),
                "mask": (
                    IO.MASK,
                    {
                        "default": None,
                        "tooltip": "Optional mask for inpainting (white areas will be replaced)",
                    },
                ),
            },
            "hidden": {"auth_token": "AUTH_TOKEN_COMFY_ORG"},
        }

    RETURN_TYPES = (IO.IMAGE,)
    FUNCTION = "api_call"
    CATEGORY = "api node/image/openai"
    DESCRIPTION = cleandoc(__doc__ or "")
    API_NODE = True

    def api_call(
        self,
        prompt,
        seed=0,
        image=None,
        mask=None,
        n=1,
        size="1024x1024",
        auth_token=None,
    ):
        model = "dall-e-2"
        path = "/proxy/openai/images/generations"
        content_type = "application/json"
        request_class = OpenAIImageGenerationRequest
        img_binary = None

        if image is not None and mask is not None:
            path = "/proxy/openai/images/edits"
            content_type = "multipart/form-data"
            request_class = OpenAIImageEditRequest

            input_tensor = image.squeeze().cpu()
            height, width, channels = input_tensor.shape
            rgba_tensor = torch.ones(height, width, 4, device="cpu")
            rgba_tensor[:, :, :channels] = input_tensor

            if mask.shape[1:] != image.shape[1:-1]:
                raise Exception("Mask and Image must be the same size")
            rgba_tensor[:, :, 3] = 1 - mask.squeeze().cpu()

            rgba_tensor = downscale_image_tensor(rgba_tensor.unsqueeze(0)).squeeze()

            image_np = (rgba_tensor.numpy() * 255).astype(np.uint8)
            img = Image.fromarray(image_np)
            img_byte_arr = io.BytesIO()
            img.save(img_byte_arr, format="PNG")
            img_byte_arr.seek(0)
            img_binary = img_byte_arr  # .getvalue()
            img_binary.name = "image.png"
        elif image is not None or mask is not None:
            raise Exception("Dall-E 2 image editing requires an image AND a mask")

        # Build the operation
        operation = SynchronousOperation(
            endpoint=ApiEndpoint(
                path=path,
                method=HttpMethod.POST,
                request_model=request_class,
                response_model=OpenAIImageGenerationResponse,
            ),
            request=request_class(
                model=model,
                prompt=prompt,
                n=n,
                size=size,
                seed=seed,
            ),
            files=(
                {
                    "image": img_binary,
                }
                if img_binary
                else None
            ),
            content_type=content_type,
            auth_token=auth_token,
        )

        response = operation.execute()

        img_tensor = validate_and_cast_response(response)
        return (img_tensor,)