# FLUX1.1 [pro] Ultra > Black Forest Labs' ultra-high resolution image generation model, an enhanced version of FLUX1.1 [pro] optimized for premium quality output ## Quick Reference - Model ID: flux1.1-pro-ultra - Creator: Black Forest Labs - Status: active - Family: flux1.1 - Base URL: https://api.lumenfall.ai/openai/v1 ## Specifications - Max Resolution: 2048x2048 - Input Modalities: text - Output Modalities: image - Supported Modes: Text to Image ## API Parameters The compiled parameter schema for this model is available via the API: `GET /v1/models/flux1.1-pro-ultra?schema=true`. ### Core Parameters - `prompt` (string) — REQUIRED: Text prompt for image generation - `seed` (integer): Random seed for reproducibility ### Size & Layout - `size` (string): Image dimensions as WxH pixels (e.g. "1024x1024") or aspect ratio (e.g. "16:9"). Values: 1563x670, 670x1564, 1365x768, 768x1365, 1254x836, 836x1254, 887x1182, 1024x1024, 1145x916, 916x1145, 1183x887 - `aspect_ratio` (string): Aspect ratio of the output image (e.g. "16:9", "1:1"). Values: 9:21, 9:16, 2:3, 3:4, 4:5, 1:1, 5:4, 4:3, 3:2, 16:9, 21:9 - `resolution` (string): Output resolution tier (e.g. "1K", "4K"). Values: 1K ### Output & Format - `response_format` (string): How to return the image. Default: url. Values: url, b64_json - `output_format` (string): Output image format. Values: png, jpeg, gif, webp, avif - `output_compression` (integer): Compression level for lossy formats (JPEG, WebP, AVIF) - `n` (integer): Number of images to generate. Default: 1 ### Additional Parameters - `prompt_enhancement` (string): Whether an LLM rewrites/expands the prompt before generation (off, on). Values: off, on - `image_prompt` (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.. Only available via replicate - `image_prompt_strength` (number): The strength of the image prompt, between 0 and 1. - `raw` (boolean): Generate less processed, more natural-looking images. - `safety_tolerance` (string): The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive.. Values: 1, 2, 3, 4, 5, 6 - `sync_mode` (boolean): If `True`, the media will be returned as a data URI and the output data won't be available in the request history.. Only available via fal ## Model Identifiers - Primary Slug: flux1.1-pro-ultra - Aliases: flux-pro-1.1-ultra ## Dates - Released: November 2024 ## Tags image-generation, text-to-image, photorealistic, high-quality ## Available Providers ### fal.ai - Config Key: fal/flux1.1-pro-ultra - Provider Model ID: fal-ai/flux-pro/v1.1-ultra - Pricing: $0.060/image - Source: https://fal.ai/models/fal-ai/flux-pro/v1.1-ultra ### Replicate - Config Key: replicate/flux1.1-pro-ultra - Provider Model ID: black-forest-labs/flux-1.1-pro-ultra - Pricing: $0.060/image - Source: https://replicate.com/black-forest-labs/flux-1.1-pro-ultra ## Arena Benchmarks ### Magic Burger Explosion: Fiery Photorealism Challenge - Elo: 1138 - Record: 3W / 1L / 0T (4 battles) - Rank: #23 of 69 ### Adorable Baby Animals in Sunny Meadow - Elo: 1114 - Record: 2W / 2L / 0T (4 battles) - Rank: #41 of 72 ### Modern Clean Menu - Elo: 1107 - Record: 3W / 1L / 0T (4 battles) - Rank: #36 of 69 ### The Reversed Rodeo - Elo: 1106 - Record: 4W / 2L / 1T (7 battles) - Rank: #23 of 68 ### Apollo 11: Journey to Tranquility - Elo: 1105 - Record: 3W / 5L / 0T (8 battles) - Rank: #36 of 70 ### Geometric Composition - Elo: 1062 - Record: 2W / 3L / 0T (5 battles) - Rank: #61 of 70 ### The Capybara Taxi Driver - Elo: 1008 - Record: 0W / 4L / 0T (4 battles) - Rank: #54 of 69 ## Use Cases & Category Performance ### Text Rendering (Text-to-Image) - Rank: #29 of 61 - Elo: 1213 - Record: 15W / 9L / 0T (24 battles) - Win Rate: 62.5% ### Creativity (Text-to-Image) - Rank: #30 of 62 - Elo: 1213 - Record: 14W / 8L / 1T (23 battles) - Win Rate: 60.9% ### Product, Branding & Commercial (Text-to-Image) - Rank: #33 of 61 - Elo: 1204 - Record: 13W / 9L / 0T (22 battles) - Win Rate: 59.1% ### Art (Text-to-Image) - Rank: #27 of 48 - Elo: 1157 - Record: 5W / 2L / 1T (8 battles) - Win Rate: 62.5% ### Aesthetics (Text-to-Image) - Rank: #36 of 62 - Elo: 1214 - Record: 22W / 16L / 1T (39 battles) - Win Rate: 56.4% ### Photorealism (Text-to-Image) - Rank: #45 of 62 - Elo: 1158 - Record: 15W / 15L / 1T (31 battles) - Win Rate: 48.4% ### 3D Imaging & Modeling (Text-to-Image) - Rank: #43 of 58 - Elo: 1146 - Record: 4W / 3L / 0T (7 battles) - Win Rate: 57.1% ### Prompt Adherence (Text-to-Image) - Rank: #48 of 62 - Elo: 1200 - Record: 20W / 19L / 1T (40 battles) - Win Rate: 50.0% ## Image Gallery 10 images available for this model. Browse all at https://lumenfall.ai/models/black-forest-labs/flux1.1-pro-ultra/gallery ### Curated Examples - [A wide, cinematic low-angle shot of a premium, brushed aluminum camera body resting on a dark wal...](https://assets.lumenfall.ai/JN-asmOfXaWIoicv120XvKlx2WpXyD3QC2WbaAHc0h0/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/lt8dupe508taqq13vw70sln4ablg@jpeg) - [Cinematic wide shot of a master ceramicist's sun-drenched atelier. In the center, a weathered woo...](https://assets.lumenfall.ai/Se85DFDSG9aXzVvPrt3_MirFKN7ouzaESjmC4wGfJH8/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/jmmwkr283g6484ngu4el3xfdhxn4@jpeg) - [A sun-drenched artisanal bakery storefront with a large gold-leaf sign on the window reading "HON...](https://assets.lumenfall.ai/o-6_GD6P8z_1RI-mDk1_lVWRBq--NB18JybPYUyFsjI/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/kjpo42drs8ellhmj5cswd12j4ffr@jpeg) ### Arena Competition Results - [Magic Burger Explosion: Fiery Photorealism Challenge](https://assets.lumenfall.ai/HeaeBMBYHQQvZhF7lvY3XeOKXCjcJ0DY2unXySmchDA/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/3n35nfikxolu11169vugda6h7c8f@jpeg): #25 of 69 (Elo 1138) - [Adorable Baby Animals in Sunny Meadow](https://assets.lumenfall.ai/TWkqQwiJ_T6iFaOIn-yusTF4g2tfR_Mgl-8UASMYuBY/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/nn9kj6v4x7j3ihjhq005coqkog3w@jpeg): #41 of 72 (Elo 1114) - [Modern Clean Menu](https://assets.lumenfall.ai/zMxKelwuSHH28pOCmr5TE5nimyDtygFcriQlItiFwLE/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/0neezetwcw6vz3htunnrpr71zgza@jpeg): #35 of 69 (Elo 1107) - [The Reversed Rodeo](https://assets.lumenfall.ai/hd1WsJhAfqFPkKnDnX2PGlWWvzBSbGb_jY7KKinQxY4/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/m25ms6xpc8tvl9sv50bbz8p4dy60@jpeg): #24 of 68 (Elo 1106) - [Apollo 11: Journey to Tranquility](https://assets.lumenfall.ai/E1PY14OihWW3ueYGjiDgbXsIj83g5R-PpN4KhD2yRhE/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/xysbgncmm7u6t6b1kekjdat0ku2s@jpeg): #38 of 70 (Elo 1105) - [Geometric Composition](https://assets.lumenfall.ai/e6MGttJHiNGwxYlZQDulLrm6dEkPTzi0w7k_LW4vVlM/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/lr19xes6z10ldvm9sr3nd2pgwflg@jpeg): #61 of 70 (Elo 1062) - [The Capybara Taxi Driver](https://assets.lumenfall.ai/1T0vt9mEWNAr-YLeuQubtsazHE_T-xTWUKCHuGT-67M/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/w1n61q1eoj3wecnuk4j40addjbss@jpeg): #54 of 69 (Elo 1008) ## Example Prompt The following prompt was used to generate an example image in our playground: A sun-drenched artisanal bakery storefront with a large gold-leaf sign on the window reading "HONEY & RYE". In the background, a calm capybara sits patiently on the sidewalk by a bicycle, while a baker carries a tray of fresh sourdough. ## Code Examples ### Text to Image (/v1/images/generations) #### cURL curl -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": "..." }] } #### JavaScript 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); #### Python from openai import OpenAI client = 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) ## About ## 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. ## Frequently Asked Questions ### 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. ## Links - Model Page: https://lumenfall.ai/models/black-forest-labs/flux1.1-pro-ultra - About: https://lumenfall.ai/models/black-forest-labs/flux1.1-pro-ultra/about - Providers, Pricing & Performance: https://lumenfall.ai/models/black-forest-labs/flux1.1-pro-ultra/providers - API Reference: https://lumenfall.ai/models/black-forest-labs/flux1.1-pro-ultra/api - Benchmarks: https://lumenfall.ai/models/black-forest-labs/flux1.1-pro-ultra/benchmarks - Use Cases: https://lumenfall.ai/models/black-forest-labs/flux1.1-pro-ultra/use-cases - Gallery: https://lumenfall.ai/models/black-forest-labs/flux1.1-pro-ultra/gallery - Playground: https://lumenfall.ai/models/black-forest-labs/flux1.1-pro-ultra/playground - API Documentation: https://docs.lumenfall.ai