The Flux 1.1 [pro] Ultra Image node allows you to generate ultra-high-resolution images through text prompts, directly connecting to Black Forest Labs’ latest image generation API.

This node supports two main usage modes:

  1. Text-to-Image: Generate high-quality images from text prompts (when no image input is used)
  2. Image-to-Image: Combine existing images with prompts to create new images that blend features from both (Remix mode)

This node supports Ultra mode through API calls, capable of generating images at 4 times the resolution of standard Flux 1.1 [pro] (up to 4MP), without sacrificing prompt adherence, and maintaining super-fast generation times of just 10 seconds. Compared to other high-resolution models, it’s more than 2.5 times faster.

Parameter Description

Basic Parameters

ParameterTypeDefaultDescription
promptString""Text description for generating the image
prompt_upsamplingBooleanFalseWhether to use prompt upsampling technique to enhance details. When enabled, automatically modifies prompts for more creative generation, but results become non-deterministic (same seed won’t produce exactly the same result)
seedInteger0Random seed value, controls generation randomness
aspect_ratioString”16:9”Width-to-height ratio of the image, must be between 1:4 and 4:1
rawBooleanFalseWhen set to True, generates less processed, more natural-looking images

Optional Parameters

ParameterTypeDefaultDescription
image_promptImageNoneOptional input, used for Image-to-Image (Remix) mode
image_prompt_strengthFloat0.1Active when image_prompt is input, adjusts the blend between prompt and image prompt. Higher values make output closer to input image, range is 0.0-1.0

Output

OutputTypeDescription
IMAGEImageGenerated high-resolution image result

Usage Examples

Please visit the tutorial below to see corresponding usage examples

How It Works

Flux 1.1 [pro] Ultra mode uses optimized deep learning architecture and efficient GPU acceleration technology to achieve high-resolution image generation without sacrificing speed. When a request is sent to the API, the system parses the prompt, applies appropriate parameters, then computes the image in parallel, finally generating and returning the high-resolution result.

Compared to regular models, Ultra mode particularly focuses on detail preservation and consistency at large scales, ensuring impressive quality even at 4MP high resolution.

Source Code

[Node Source Code (Updated on 2025-05-03)]

class FluxProUltraImageNode(ComfyNodeABC):
    """
    Generates images synchronously based on prompt and resolution.
    """

    MINIMUM_RATIO = 1 / 4
    MAXIMUM_RATIO = 4 / 1
    MINIMUM_RATIO_STR = "1:4"
    MAXIMUM_RATIO_STR = "4:1"

    @classmethod
    def INPUT_TYPES(s):
        return {
            "required": {
                "prompt": (
                    IO.STRING,
                    {
                        "multiline": True,
                        "default": "",
                        "tooltip": "Prompt for the image generation",
                    },
                ),
                "prompt_upsampling": (
                    IO.BOOLEAN,
                    {
                        "default": False,
                        "tooltip": "Whether to perform upsampling on the prompt. If active, automatically modifies the prompt for more creative generation, but results are nondeterministic (same seed will not produce exactly the same result).",
                    },
                ),
                "seed": (
                    IO.INT,
                    {
                        "default": 0,
                        "min": 0,
                        "max": 0xFFFFFFFFFFFFFFFF,
                        "control_after_generate": True,
                        "tooltip": "The random seed used for creating the noise.",
                    },
                ),
                "aspect_ratio": (
                    IO.STRING,
                    {
                        "default": "16:9",
                        "tooltip": "Aspect ratio of image; must be between 1:4 and 4:1.",
                    },
                ),
                "raw": (
                    IO.BOOLEAN,
                    {
                        "default": False,
                        "tooltip": "When True, generate less processed, more natural-looking images.",
                    },
                ),
            },
            "optional": {
                "image_prompt": (IO.IMAGE,),
                "image_prompt_strength": (
                    IO.FLOAT,
                    {
                        "default": 0.1,
                        "min": 0.0,
                        "max": 1.0,
                        "step": 0.01,
                        "tooltip": "Blend between the prompt and the image prompt.",
                    },
                ),
            },
            "hidden": {
                "auth_token": "AUTH_TOKEN_COMFY_ORG",
            },
        }

    @classmethod
    def VALIDATE_INPUTS(cls, aspect_ratio: str):
        try:
            validate_aspect_ratio(
                aspect_ratio,
                minimum_ratio=cls.MINIMUM_RATIO,
                maximum_ratio=cls.MAXIMUM_RATIO,
                minimum_ratio_str=cls.MINIMUM_RATIO_STR,
                maximum_ratio_str=cls.MAXIMUM_RATIO_STR,
            )
        except Exception as e:
            return str(e)
        return True

    RETURN_TYPES = (IO.IMAGE,)
    DESCRIPTION = cleandoc(__doc__ or "")  # Handle potential None value
    FUNCTION = "api_call"
    API_NODE = True
    CATEGORY = "api node/image/bfl"

    def api_call(
        self,
        prompt: str,
        aspect_ratio: str,
        prompt_upsampling=False,
        raw=False,
        seed=0,
        image_prompt=None,
        image_prompt_strength=0.1,
        auth_token=None,
        **kwargs,
    ):
        operation = SynchronousOperation(
            endpoint=ApiEndpoint(
                path="/proxy/bfl/flux-pro-1.1-ultra/generate",
                method=HttpMethod.POST,
                request_model=BFLFluxProUltraGenerateRequest,
                response_model=BFLFluxProGenerateResponse,
            ),
            request=BFLFluxProUltraGenerateRequest(
                prompt=prompt,
                prompt_upsampling=prompt_upsampling,
                seed=seed,
                aspect_ratio=validate_aspect_ratio(
                    aspect_ratio,
                    minimum_ratio=self.MINIMUM_RATIO,
                    maximum_ratio=self.MAXIMUM_RATIO,
                    minimum_ratio_str=self.MINIMUM_RATIO_STR,
                    maximum_ratio_str=self.MAXIMUM_RATIO_STR,
                ),
                raw=raw,
                image_prompt=(
                    image_prompt
                    if image_prompt is None
                    else convert_image_to_base64(image_prompt)
                ),
                image_prompt_strength=(
                    None if image_prompt is None else round(image_prompt_strength, 2)
                ),
            ),
            auth_token=auth_token,
        )
        output_image = handle_bfl_synchronous_operation(operation)
        return (output_image,)