Black Forest Labs
FLUX.2 [max]
Black Forest Labs' flagship image generation model delivering state-of-the-art quality with exceptional realism, precision, and consistency for both text-to-image and advanced image editing
Explore ModelBlack Forest Labs
6 AI Image Generation Models and 7 AI Image Editing Models
Models
13 modelsBlack Forest Labs' enhanced 12-billion parameter flow transformer with 6x faster generation than FLUX.1 [pro], delivering superior composition, detail, and artistic fidelity
Black Forest Labs' ultra-high resolution image generation model, an enhanced version of FLUX1.1 [pro] optimized for premium quality output
Black Forest Labs' 12-billion parameter flow transformer for high-quality text-to-image generation, suitable for personal and commercial use with streaming support
Black Forest Labs' open-weights multimodal flow transformer for in-context image generation and editing, available for non-commercial use with character consistency and style transfer capabilities
Black Forest Labs' premium multimodal flow transformer with greatly improved prompt adherence and typography generation for in-context image generation and editing without compromise on speed
Black Forest Labs' 12-billion parameter multimodal flow transformer for in-context image generation and editing with character consistency, typography handling, and commercial-ready quality
Black Forest Labs' aesthetically-tuned 12-billion parameter flow transformer optimized for high-quality images with incredible aesthetics, suitable for personal and commercial use
Black Forest Labs' 12 billion parameter distilled image generation model optimized for speed, capable of generating high-quality images in just 4 inference steps
FP8 quantized variant of Black Forest Labs' FLUX.1 [schnell] model, offering ~2x faster inference with reduced precision while maintaining high-quality image generation in 4 steps
Black Forest Labs' open-weights image generation model with frontier performance, available for non-commercial local deployment
Black Forest Labs' precision image generation model with maximum control, reliable text rendering, and complete creative control supporting up to 4MP output
Black Forest Labs' flagship image generation model delivering state-of-the-art quality with exceptional realism, precision, and consistency for both text-to-image and advanced image editing
Black Forest Labs' state-of-the-art image generation model with maximum quality and speed, supporting text-to-image and multi-reference image editing with up to 4MP output
Examples
20 imagesArena Rankings
Text to Image
View full leaderboard| # | Model | Elo |
|---|---|---|
| 5 | FLUX.2 [max] | 1265 |
|
3 more models
|
||
| 9 | FLUX.2 [pro] | 1255 |
|
6 more models
|
||
| 16 | FLUX.2 [flex] | 1239 |
| 17 | FLUX.2 [dev] | 1236 |
|
10 more models
|
||
27 models ranked
Image Editing
View full leaderboard| # | Model | Elo |
|---|---|---|
| 5 | FLUX.2 [flex] | 1228 |
|
4 more models
|
||
| 10 | FLUX.2 [pro] | 1202 |
|
1 more model
|
||
| 12 | FLUX.2 [max] | 1192 |
|
4 more models
|
||
16 models ranked
About Black Forest Labs
Black Forest Labs consists of a team of researchers and engineers focused on developing state-of-the-art generative deep learning models for media. Based in Germany, the organization is primarily known for the FLUX series of models, which utilizes a flow-based transformer architecture to achieve high levels of visual fidelity and prompt adherence. Their work bridges the gap between open-weight research and high-performance commercial APIs, making them a central player in the text-to-image and image-editing landscape.
- FLUX.2 [max]: The flagship model in their lineup, ranking highly on industry leaderboards for text-to-image generation. It is engineered for state-of-the-art realism and precision, delivering consistent results for both complex creative generations and advanced image editing tasks.
- FLUX1.1 [pro]: An enhanced 12-billion parameter flow transformer that prioritizes speed and efficiency. It generates images approximately six times faster than the original [pro] version while maintaining superior composition and artistic detail.
- FLUX.1 Kontext [pro]: A specialized multimodal model designed for in-context image generation and editing. It excels at maintaining character consistency across different frames and handles typography and style transfer with commercial-grade quality.
- FLUX.1 [schnell]: A distilled version of their visual transformer optimized for near-instant results. It is capable of producing high-quality images in as few as four inference steps, making it ideal for real-time applications and rapid prototyping.
- FLUX.2 [flex]: A precision-oriented model that offers maximum creative control and reliable text rendering. It is particularly strong in image editing workflows, where it ranks among the top models for maintaining structural integrity during modifications.
Black Forest Labs excels at balancing parameter count with efficient sampling techniques, resulting in models that follow intricate instructions without losing fine-grained texture or anatomical accuracy. Their architecture is particularly robust for rendering complex typography and achieving high aesthetic scores across diverse artistic styles. Developers can access the full suite of Black Forest Labs models through Lumenfall’s unified API to integrate these frontier image generation capabilities into their own applications.
Top Matchups
Head-to-head results between Black Forest Labs models and competitors, based on community votes in blind comparisons.
FLUX.2 [flex] vs Nano Banana Pro
Night Sky Transformation
13% W · 88% L
FLUX.2 [max] vs Nano Banana
Neutral Expression to Genuine Smile
0% W · 100% L
FLUX.2 [pro] vs Stable Diffusion 3.5 Large
Apollo 11: Journey to Tranquility
20% W · 80% L
FLUX.2 [flex] vs Nano Banana Pro
Man and Car in California
75% W · 25% L
FLUX.2 [max] vs Stable Diffusion 3.5 Large
Apollo 11: Journey to Tranquility
50% W · 50% L
FLUX.2 [pro] vs Nano Banana
Heroic Super Hero Portrait
25% W · 25% L · 50% T
FLUX.2 [dev] vs Lucid Origin
Fantasy Warrior
0% W · 100% L