Flux Pro V1.1 Ultra API

V1.1 Ultra
Redux

Endpoint: POST https://fal.run/fal-ai/flux-pro/v1.1-ultra Endpoint ID: fal-ai/flux-pro/v1.1-ultra

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "fal-ai/flux-pro/v1.1-ultra",
    arguments={
        "prompt": "Extreme close-up of a single tiger eye, direct frontal view. Detailed iris and pupil. Sharp focus on eye texture and color. Natural lighting to capture authentic eye shine and depth. The word \"FLUX\" is painted over it in big, white brush strokes with visible texture."
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

Input Schema

prompt

string

required

The prompt to generate an image from.

seed

integer

The same seed and the same prompt given to the same version of the model will output the same image every time.

sync_mode

boolean

default:"false"

If True, the media will be returned as a data URI and the output data won’t be available in the request history.

num_images

integer

default:"1"

The number of images to generate. Default value: 1Range: 1 to 4

output_format

OutputFormatEnum

default:"jpeg"

The format of the generated image. Default value: "jpeg"Possible values: jpeg, png

safety_tolerance

SafetyToleranceEnum

default:"2"

The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive. Default value: "2"Possible values: 1, 2, 3, 4, 5, 6

enhance_prompt

boolean

default:"false"

Whether to enhance the prompt for better results.

image_url

string

The image URL to generate an image from.

image_prompt_strength

float

default:"0.1"

The strength of the image prompt, between 0 and 1. Default value: 0.1Range: 0 to 1

aspect_ratio

Enum | string

default:"16:9"

The aspect ratio of the generated image. Default value: 16:9Possible values: 21:9, 16:9, 4:3, 3:2, 1:1, 2:3, 3:4, 9:16, 9:21

raw

boolean

default:"false"

Generate less processed, more natural-looking images.

Output Schema

images

list<registry__image__fast_sdxl__models__Image>

required

The generated image files info.

timings

Timings

required

seed

integer

required

Seed of the generated Image. It will be the same value of the one passed in the input or the randomly generated that was used in case none was passed.

has_nsfw_concepts

list<boolean>

required

Whether the generated images contain NSFW concepts.

prompt

string

required

The prompt used for generating the image.

Input Example

{
  "prompt": "Extreme close-up of a single tiger eye, direct frontal view. Detailed iris and pupil. Sharp focus on eye texture and color. Natural lighting to capture authentic eye shine and depth. The word \"FLUX\" is painted over it in big, white brush strokes with visible texture.",
  "sync_mode": false,
  "num_images": 1,
  "output_format": "jpeg",
  "safety_tolerance": "2",
  "enhance_prompt": false,
  "image_prompt_strength": 0.1,
  "aspect_ratio": "16:9",
  "raw": false
}

Output Example

{
  "images": [
    {
      "url": "",
      "content_type": "image/jpeg"
    }
  ],
  "prompt": ""
}

Endpoint: POST https://fal.run/fal-ai/flux-pro/v1.1-ultra/redux Endpoint ID: fal-ai/flux-pro/v1.1-ultra/redux

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "fal-ai/flux-pro/v1.1-ultra/redux",
    arguments={
        "image_url": "https://fal.media/files/kangaroo/acQvq-Kmo2lajkgvcEHdv.png"
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

Input Schema

prompt

string

default:""

The prompt to generate an image from. Default value: ""

seed

integer

The same seed and the same prompt given to the same version of the model will output the same image every time.

sync_mode

boolean

default:"false"

If True, the media will be returned as a data URI and the output data won’t be available in the request history.

num_images

integer

default:"1"

The number of images to generate. Default value: 1Range: 1 to 4

output_format

OutputFormatEnum

default:"jpeg"

The format of the generated image. Default value: "jpeg"Possible values: jpeg, png

safety_tolerance

SafetyToleranceEnum

default:"2"

The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive. Default value: "2"Possible values: 1, 2, 3, 4, 5, 6

enhance_prompt

boolean

default:"false"

Whether to enhance the prompt for better results.

image_url

string

required

The image URL to generate an image from. Needs to match the dimensions of the mask.

image_prompt_strength

float

default:"0.1"

The strength of the image prompt, between 0 and 1. Default value: 0.1Range: 0 to 1

aspect_ratio

Enum | string

default:"16:9"

The aspect ratio of the generated image. Default value: 16:9Possible values: 21:9, 16:9, 4:3, 3:2, 1:1, 2:3, 3:4, 9:16, 9:21

raw

boolean

default:"false"

Generate less processed, more natural-looking images.

Output Schema

images

list<registry__image__fast_sdxl__models__Image>

required

The generated image files info.

timings

Timings

required

seed

integer

required

Seed of the generated Image. It will be the same value of the one passed in the input or the randomly generated that was used in case none was passed.

has_nsfw_concepts

list<boolean>

required

Whether the generated images contain NSFW concepts.

prompt

string

required

The prompt used for generating the image.

Input Example

{
  "prompt": "",
  "sync_mode": false,
  "num_images": 1,
  "output_format": "jpeg",
  "safety_tolerance": "2",
  "enhance_prompt": false,
  "image_url": "https://fal.media/files/kangaroo/acQvq-Kmo2lajkgvcEHdv.png",
  "image_prompt_strength": 0.1,
  "aspect_ratio": "16:9",
  "raw": false
}

Output Example

{
  "images": [
    {
      "url": "",
      "content_type": "image/jpeg"
    }
  ],
  "prompt": ""
}

Black Forest Labs’ FLUX1.1 [pro] ultra delivers up to 2K resolution (4 megapixels) image generation at $0.06 per image. With 4x the resolution detail, this model extends FLUX1.1 [pro]‘s capabilities with enhanced photorealism while maintaining ~10 second generation times. Built for production workflows where resolution and visual fidelity directly impact deliverables. Use Cases: High-resolution marketing assets | Product photography | Editorial illustrations

Performance

At $0.06 per image with 4-megapixel output capability, FLUX1.1 [pro] ultra positions between standard-resolution alternatives and premium high-res solutions.

Metric	Result	Context
Max Resolution	4 megapixels (2048×2048)	4x standard FLUX1.1 [pro] resolution
Inference Speed	~10 seconds per sample	Ultra mode generation time from Black Forest Labs
Cost per Image	$0.06	16.7 images per $1.00
Batch Generation	Up to 4 images	Parallel generation via `num_images` parameter
Related Endpoints	FLUX1.1 [pro], FLUX.1 Kontext [pro]	Standard resolution and context-aware variants

Professional-Grade Resolution Without Compromise

FLUX1.1 [pro] ultra extends Black Forest Labs’ architecture to 4-megapixel generation while maintaining the prompt interpretation and photorealism that defined the standard version. Where most high-resolution models sacrifice inference speed or introduce quality degradation, ultra mode processes at comparable latency to standard-resolution alternatives. What this means for you:

True 2K output: Generate up to 2048×2048 images without upscaling artifacts or post-processing, delivering print-ready assets directly from the API
Optional image conditioning: Use image_url and image_prompt_strength (0-1 range) to guide generation with reference images, enabling style transfer and composition control
Flexible aspect ratios: Support for multiple aspect ratios with automatic megapixel-based billing, pay only for the resolution you actually use
Granular safety controls: Six-level safety_tolerance parameter (1-6) lets you calibrate content filtering for your specific use case, from strict (1) to permissive (6)

Technical Specifications

Spec	Details
Architecture	FLUX1.1 [pro] ultra
Input Formats	Text prompts, optional reference images via URL
Output Formats	JPEG, PNG
Max Resolution	4 megapixels (up to 2048×2048)
License	Commercial use enabled via fal partnership

API Documentation | Quickstart Guide | Enterprise Pricing

How It Stacks Up

**FLUX1.1 [pro] (

0.05)** – FLUX1.1 [pro] ultra trades cost efficiency for 4x resolution at

0.06 vs $0.05 (20% premium). Standard FLUX1.1 [pro] remains ideal for high-volume workflows where 1-megapixel output meets requirements and cost per image is the primary constraint. FLUX.1 Kontext [pro] ($0.05) – FLUX1.1 [pro] ultra prioritizes maximum resolution and photorealism for single-image generation. FLUX.1 Kontext [pro] emphasizes multi-image context understanding (up to 5 reference images) at standard resolution, optimized for workflows requiring consistent style or character preservation across generations. **AuraFlow (

0.012)** – FLUX1.1 [pro] ultra delivers professional-grade photorealism and 4-megapixel output at 5x the cost (

0.06 vs $0.012). AuraFlow offers open-weight flexibility and cost efficiency for rapid iteration workflows where resolution and photorealism requirements are secondary to generation volume.

FLUX1.1 [pro] — Image Generation
FLUX.1 [pro] Fill — Image Generation
FLUX1.1 [pro] Redux — Image Generation
FLUX1.1 [pro] ultra Redux — Image Generation
FLUX1.1 [pro] ultra Fine-tuned — Image Generation
FLUX.1 [pro] Fill Fine-tuned — Image Generation
FLUX1.1 [pro] ultra — Image Generation

Limitations

num_images range: 1 to 4
output_format restricted to: jpeg, png
safety_tolerance restricted to: 1, 2, 3, 4, 5, 6
image_prompt_strength range: 0 to 1

Video Generation

Image Generation

Audio

Vision

3D

Flux Pro V1.1 Ultra API

Try it in the Playground

Quick Start

Input Schema

Output Schema

Input Example

Output Example

Try it in the Playground

Quick Start

Input Schema

Output Schema

Input Example

Output Example

Performance

Professional-Grade Resolution Without Compromise

Technical Specifications

How It Stacks Up

Limitations

Video Generation

Image Generation

Audio

Vision

3D

Try it in the Playground

​Quick Start

​Input Schema

​Output Schema

​Input Example

​Output Example

Try it in the Playground

​Quick Start

​Input Schema

​Output Schema

​Input Example

​Output Example

​Performance

​Professional-Grade Resolution Without Compromise

​Technical Specifications

​How It Stacks Up

​Related

​Limitations

Quick Start

Input Schema

Output Schema

Input Example

Output Example

Quick Start

Input Schema

Output Schema

Input Example

Output Example

Performance

Professional-Grade Resolution Without Compromise

Technical Specifications

How It Stacks Up

Related

Limitations