Black Forest Labs' ultra-high resolution image generation model, an enhanced version of FLUX1.1 [pro] optimized for premium quality output
Details
flux1.1-pro-ultra
Starting from
Prices shown are in USD
See all providersProviders & Pricing (2)
FLUX1.1 [pro] Ultra is available from 2 providers, with per-image pricing starting at $0.06 through fal.ai.
fal/flux1.1-pro-ultra
replicate/flux1.1-pro-ultra
flux-pro-1.1-ultra API OpenAI-compatible
Integrate Black Forest Labs' premium FLUX1.1 [pro] Ultra model via Lumenfall’s OpenAI-compatible API to generate high-fidelity, professional-grade images from text prompts.
https://api.lumenfall.ai/openai/v1
flux1.1-pro-ultra
Code Examples
Text to Image
/v1/images/generationscurl -X POST \ https://api.lumenfall.ai/openai/v1/images/generations \ -H "Authorization: Bearer $LUMENFALL_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "flux1.1-pro-ultra", "prompt": "", "size": "1024x1024" }'# Response:# { "created": 1234567890, "data": [{ "url": "https://...", "revised_prompt": "..." }] }import OpenAI from 'openai';const client = new OpenAI({ apiKey: 'YOUR_API_KEY', baseURL: 'https://api.lumenfall.ai/openai/v1'});const response = await client.images.generate({ model: 'flux1.1-pro-ultra', prompt: '', size: '1024x1024'});// { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }console.log(response.data[0].url);from openai import OpenAIclient = OpenAI( api_key="YOUR_API_KEY", base_url="https://api.lumenfall.ai/openai/v1")response = client.images.generate( model="flux1.1-pro-ultra", prompt="", size="1024x1024")# { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }print(response.data[0].url)Parameter Reference
Core Parameters
| Parameter | Type | Description | Modes |
|---|---|---|---|
prompt
|
string | Required. Text prompt for image generation |
T2I
|
seed
|
integer | Random seed for reproducibility |
T2I
|
Size & Layout
| Parameter | Type | Description | Modes |
|---|---|---|---|
size
|
string |
Image dimensions as WxH pixels (e.g. "1024x1024") or aspect ratio (e.g. "16:9")
WxH determines both shape and scale (aspect_ratio and resolution are ignored when size is provided). W:H format is equivalent to aspect_ratio.
|
T2I
|
aspect_ratio
|
string |
Aspect ratio of the output image (e.g. "16:9", "1:1")
Controls shape independently of scale. Use with resolution to control both. If size is also provided, size takes precedence. Any ratio is accepted and mapped to the nearest supported value.
|
T2I
|
resolution
|
string |
Output resolution tier (e.g. "1K", "4K")
1K
Controls scale independently of shape. Higher tiers produce larger images and cost more. If size is also provided, size takes precedence for scale. Any tier is accepted and mapped to the nearest supported value.
|
T2I
|
1K 11 sizes
| Output |
size
|
aspect_ratio
+
resolution
|
|
|---|---|---|---|
| 1183 × 887 | "1183x887" |
or |
"4:3"
+
"1K"
|
| 916 × 1145 | "916x1145" |
or |
"4:5"
+
"1K"
|
| 1145 × 916 | "1145x916" |
or |
"5:4"
+
"1K"
|
| 1024 × 1024 | "1024x1024" |
or |
"1:1"
+
"1K"
|
| 887 × 1182 | "887x1182" |
or |
"3:4"
+
"1K"
|
| 836 × 1254 | "836x1254" |
or |
"2:3"
+
"1K"
|
| 1254 × 836 | "1254x836" |
or |
"3:2"
+
"1K"
|
| 768 × 1365 | "768x1365" |
or |
"9:16"
+
"1K"
|
| 1365 × 768 | "1365x768" |
or |
"16:9"
+
"1K"
|
| 670 × 1564 | "670x1564" |
or |
"9:21"
+
"1K"
|
| 1563 × 670 | "1563x670" |
or |
"21:9"
+
"1K"
|
How these parameters work
size
Exact pixel dimensions
"1920x1080"
aspect_ratio
Shape only, default scale
"16:9"
resolution
Scale tier, preserves shape
"1K"
Priority when combined
size is most specific and always wins. aspect_ratio and resolution control shape and scale independently.
How matching works
7:1 on a model with
4:1 and 8:1,
you get 8:1.
0.5K 1K 2K 4K)
or megapixel tiers (0.25 1).
If the exact tier isn't available, you get the nearest one.
Output & Format
| Parameter | Type | Description | Modes |
|---|---|---|---|
response_format
|
string |
How to return the image
url
b64_json
Default:
"url" |
T2I
|
output_format
|
string |
Output image format
png
jpeg
gif
webp
avif
Gateway converts to requested format if provider doesn't support it natively.
|
T2I
|
output_compression
|
integer | Compression level for lossy formats (JPEG, WebP, AVIF) |
T2I
|
n
|
integer |
Number of images to generate
Default:
1Gateway generates multiple images in parallel even if provider only supports 1.
|
T2I
|
Additional Parameters
| Parameter | Type | Description | Modes |
|---|---|---|---|
enhance_prompt
fal
|
boolean | Whether to enhance the prompt for better results. |
T2I
|
image_prompt
replicate
|
string | Image to use with Flux Redux. This is used together with the text prompt to guide the generation towards the composition of the image_prompt. Must be jpeg, png, gif, or webp. |
T2I
|
image_prompt_strength
|
number | The strength of the image prompt, between 0 and 1. |
T2I
|
raw
|
boolean | Generate less processed, more natural-looking images. |
T2I
|
safety_tolerance
|
string |
The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive.
1
2
3
4
5
6
|
T2I
|
sync_mode
fal
|
boolean | If `True`, the media will be returned as a data URI and the output data won't be available in the request history. |
T2I
|
Parameter Normalization
How we handle parameters across different providers
Not every provider speaks the same language. When you send a parameter, we handle it in one of four ways depending on what the model supports:
| Behavior | What happens | Example |
|---|---|---|
passthrough |
Sent as-is to the provider | style, quality |
renamed |
Same value, mapped to the field name the provider expects | prompt |
converted |
Transformed to the provider's native format | size |
emulated |
Works even if the provider has no concept of it | n, response_format |
Parameters we don't recognize pass straight through to the upstream API, so provider-specific options still work.
Gallery
View all 3 imagesFLUX1.1 [pro] Ultra FAQ
How much does FLUX1.1 [pro] Ultra cost?
FLUX1.1 [pro] Ultra starts at $0.06 per image through Lumenfall. Pricing varies by provider. Lumenfall does not add any markup to provider pricing.
How do I use FLUX1.1 [pro] Ultra via API?
You can use FLUX1.1 [pro] Ultra through Lumenfall's OpenAI-compatible API. Send requests to the unified endpoint with model ID "flux1.1-pro-ultra". Code examples are available in Python, JavaScript, and cURL.
Which providers offer FLUX1.1 [pro] Ultra?
FLUX1.1 [pro] Ultra is available through fal.ai and Replicate on Lumenfall. Lumenfall automatically routes requests to the best available provider.
What is the maximum resolution for FLUX1.1 [pro] Ultra?
FLUX1.1 [pro] Ultra supports images up to 2048x2048 resolution.
Overview
FLUX1.1 [pro] Ultra is a high-resolution text-to-image model developed by Black Forest Labs. As an enhanced evolution of the standard FLUX1.1 [pro] architecture, it is specifically engineered to produce premium, photography-grade outputs at significantly higher pixel counts. The model is distinctive for its ability to maintain compositional coherence and fine-textured detail while operating at extreme resolutions.
Strengths
- Ultra-High Resolution Output: Unlike base models that often degrade or repeat patterns at high resolutions, this version is optimized for large-scale generations up to 4 megapixels while maintaining structural integrity.
- Photorealistic Texture Rendering: The model excels at reproducing complex surface details, such as skin pores, fabric weaves, and atmospheric effects, making it suitable for professional-grade photography emulation.
- Improved Prompt Adherence: It demonstrates high fidelity to complex, multi-part instructions, accurately placing objects and satisfying specific lighting or stylistic requirements defined in the prompt.
- Speed Efficiency: Despite the increase in output resolution and quality, the model maintains the competitive inference speeds introduced with the FLUX1.1 architecture, offering a faster workflow than many comparable high-resolution diffusion models.
Limitations
- Cost Per Generation: With a starting price of roughly $0.06 per image, it is significantly more expensive than “dev” or “schnell” variants, making it less ideal for rapid prototyping or high-volume testing.
- Hardware and Latency: Generating images at ultra-high resolutions requires substantial VRAM and compute time; even with optimizations, the time-to-first-pixel is longer than the standard FLUX1.1 [pro] version.
- Over-Refinement: In certain artistic contexts, the model’s bias toward “premium” and sharp textures may result in an overly polished look that requires specific prompting to achieve a more muted or “lo-fi” aesthetic.
Technical Background
FLUX1.1 [pro] Ultra is built upon the Flow-based transformer architecture characteristic of the Black Forest Labs lineup. It utilizes a rectified flow scaling approach, which streamlines the sampling process to achieve high-quality results in fewer steps than traditional latent diffusion models. The “Ultra” designation refers to specific fine-tuning and scaling adjustments designed to handle expanded canvas sizes without the tiling artifacts common in earlier diffusion generations.
Best For
This model is best suited for professional workflows where final-asset quality is paramount, such as digital advertising, high-fidelity concept art, and print-ready media. It shines in scenarios requiring hyper-realistic human portraits or intricate architectural visualizations.
FLUX1.1 [pro] Ultra is available through Lumenfall’s unified API and playground, allowing developers to integrate ultra-high resolution image generation into their applications with a single standardized interface.
Try FLUX1.1 [pro] Ultra in Playground
Generate images with custom prompts — no API key needed.