inference · 13.2s

Flux 1.1 Pro

Image·flux-1.1·by Black Forest Labs

Faster, better FLUX Pro. Text-to-image model with excellent image quality, prompt adherence, and output diversity.

Try it now →

API reference

Runtime (p50): 8s
Estimated price: $0.04

Call the API

prediction.sh

curl -X POST \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Content-Type: application/json" \
  --data '{
    "model": "flux-1-1-pro",
    "version": "0.0.1",
    "input": {
        "prompt": "Ultra realistic woman, IMG_5432.HEIC, nyc background",
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "output_quality": 80,
        "safety_tolerance": 2,
        "prompt_upsampling": true
    },
    "webhook_url": ""
}' \
  https://api.eachlabs.ai/v1/prediction/

Documentation8 sections

Overview
flux-1.1-pro — Text-to-Image AI Model

flux-1.1-pro from Black Forest Labs delivers faster generation speeds up to 6x quicker than previous models while maintaining exceptional image quality, making it the go-to text-to-image AI model for professional workflows demanding speed and reliability. Developed as part of the flux-1.1 family, this 12B parameter model excels in prompt adherence, output diversity, and consistent results ideal for batch production in commercial design and marketing. Whether you're seeking a Black Forest Labs text-to-image solution or flux-1.1-pro API integration, it produces vivid, realistic images with precise anatomy, lighting, and materials in seconds.
Capabilities
Rapid Generation: Delivers images six times faster than previous versions, enhancing real-time application feasibility.

High-Resolution Outputs: Supports ultra high-resolution image generation up to 2K, maintaining prompt fidelity.

Improved hardware efficiency

Superior text prompt compliance

Enhanced output diversity
Use cases
Use Cases for flux-1.1-pro

Product marketers building AI image generators for e-commerce can input prompts like "A luxury watch on a textured leather surface with soft studio lighting and subtle reflections" to create consistent, high-fidelity renders that showcase products realistically without photoshoots, streamlining catalog updates.

Portrait photographers and designers use flux-1.1-pro for batch-generating diverse headshots with natural expressions and anatomy, such as cyberpunk fashion portraits or executive profiles against city skylines, leveraging its stability for client galleries and advertising.

Developers integrating text-to-image AI models into apps benefit from its fast 12B parameter processing and aspect ratio flexibility, producing 2K social media assets or presentation visuals in under 30 seconds per image.

Creative agencies handling Black Forest Labs text-to-image tasks for sci-fi concepts generate futuristic outfits with holographic effects and neon lighting, capitalizing on superior material representation for concept art and promotional materials.
Tips & tricks
How to Use flux-1.1-pro on Eachlabs

Access flux-1.1-pro seamlessly through Eachlabs Playground for instant testing, API for production-scale integrations, or SDK for custom apps. Provide a detailed text prompt specifying subjects, styles, lighting, and mood; select aspect ratios like 16:9 or 1:1, toggle raw mode for natural aesthetics, and choose PNG/JPG output. Expect high-quality 2K images in seconds with excellent prompt adherence and diversity.
---
Technical spec
What Sets flux-1.1-pro Apart

flux-1.1-pro stands out with its optimized inference pipeline enabling 6x faster generation compared to prior iterations, allowing professionals to produce high-quality images rapidly for time-sensitive projects like marketing campaigns. This speed supports resolutions up to 2K (2048x2048) and multiple aspect ratios including 1:1, 16:9, 9:16, 4:3, and 3:4, covering everything from social media graphics to print-ready visuals. It also offers raw mode for less processed, naturally aesthetic outputs that mimic professional photography without the typical AI polish.
- Outstanding stability for batch creation: Generates highly consistent portraits, product renders, and designs with accurate facial proportions and vivid expressions, perfect for commercial-scale production.
- Delicate material and lighting realism: Renders textures, shadows, and lighting with photorealistic precision, outperforming many models in visual fidelity for e-commerce and creative applications.
- Ultra-high resolution support: Handles up to 4MP outputs with raw mode, enabling detailed images suitable for professional prints and large displays.
Things to be aware of
Style Exploration: Experiment with prompts that specify different artistic styles, such as "a surrealist painting of a cityscape at dawn."

Scene Composition: Create complex scenes by detailing elements and their interactions, like "a futuristic marketplace bustling with diverse alien species."

Abstract Concepts: Test the model's interpretative capabilities with abstract prompts, such as "the essence of tranquility depicted in shades of blue."

Generate realistic photos using the 'IMG_XXXX_CR2' format

Create professional product photography with simple one-word prompts

Generate images with varying levels of prompt complexity

Try portrait photography with natural lighting and poses

Experiment with landscape photography in different conditions

Create realistic stock photo alternatives

Generate concept art with different artistic styles

Test the model's capabilities with architectural visualization

Compare results between simple and complex prompts
Key considerations
Ethical Use: Ensure that generated images comply with ethical guidelines and do not infringe upon copyright or promote harmful content.

Licensing: By using FLUX1.1 [pro], users agree to the Black Forest Labs API agreement and Terms of Service.

Six times faster generation than its predecessor FLUX.1 Pro
Based on a hybrid architecture of multimodal and parallel diffusion transformer blocks

Scaled to 12B parameters

Built on flow matching, a general method for training generative models

Incorporates rotary positional embeddings and parallel attention layers

Legal Information
By using this model, you agree to:
- Black Forest Labs API agreement
- Black Forest Labs Terms of Service
Limitations
Input Constraints: While the model excels with well-crafted text prompts, ambiguous or poorly defined prompts may lead to less satisfactory results.

Output Variability: Despite improved prompt adherence, some generated images may not fully capture complex or highly detailed scene descriptions.

Resource Requirements: High-resolution image generation may demand substantial computational resources, potentially impacting performance on lower-end hardware.

Some complex prompts may result in overly polished images

Performance may vary based on prompt complexity

Output Format: PNG, JPG