FLUX.1 Models by Black Forest Labs
Details
Capabilities
Links
WebsiteAbout
FLUX.1 is Black Forest Labs' flagship series of text-to-image models, launched in August 2024. Built on a hybrid architecture of rectified flow transformers and parallel diffusion transformer blocks with 12 billion parameters, the family includes Schnell (distilled, 1–4 steps), Dev (open-weight, guidance-distilled), Pro (commercial API), Pro 1.1 (improved quality), Pro 1.1 Ultra (high-resolution), and Kontext Pro (context-aware editing). FLUX.1 models set new benchmarks in visual quality, prompt adherence, and typography at launch.
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
Use when the workload needs image generation, 12K parameters, and multimodal inputs.
Use when the workload needs image generation, 12K parameters, and multimodal inputs.
Use when the workload needs image generation, 12K parameters, and multimodal inputs.
Use when the workload needs image generation, 12K parameters, and multimodal inputs.
Use when the workload needs image generation, 12K parameters, and multimodal inputs.
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| FLUX.1 Kontext [pro] | Use when the workload needs image generation, 12K parameters, and multimodal inputs. | 2025-05 | image generation12K parametersmultimodal inputs | Current |
| FLUX.1.1 [pro] Ultra | Use when the workload needs image generation, 12K parameters, and multimodal inputs. | 2024-11 | image generation12K parametersmultimodal inputs | Current |
| FLUX.1.1 [pro] | Use when the workload needs image generation, 12K parameters, and multimodal inputs. | 2024-10 | image generation12K parametersmultimodal inputs | Current |
| FLUX.1 [schnell] | Use when the workload needs image generation, 12K parameters, and multimodal inputs. | 2024-08 | image generation12K parametersmultimodal inputs | Current |
| FLUX.1 [dev] | Use when the workload needs image generation, 12K parameters, and multimodal inputs. | 2024-08 | image generation12K parametersmultimodal inputs | Current |
Release Timeline
4 release groupsSpecifications(5 models)
| Model | Released | Parameters | Multimodal |
|---|---|---|---|
| FLUX.1 Kontext [pro] | 2025-05 | 12K | Yes |
| FLUX.1.1 [pro] Ultra | 2024-11 | 12K | Yes |
| FLUX.1.1 [pro] | 2024-10 | 12K | Yes |
| FLUX.1 [schnell] | 2024-08 | 12K | Yes |
| FLUX.1 [dev] | 2024-08 | 12K | Yes |
Available From(4 providers)
Frequently Asked Questions
- What is FLUX.1 used for?
- FLUX.1 is used for image generation and vision and multimodal work. The family description and listed model capabilities point to those workloads as the best fit.
- How does FLUX.1 compare to FLUX.2?
- FLUX.1 by Black Forest Labs is strongest where you need image generation, while FLUX.2 by Black Forest Labs is the closest related family to check for image generation. FLUX.1 has 5 listed variants, so compare the specs and pricing tables before choosing a production model.
- Which FLUX.1 model should I use?
- If price is the main constraint, use the pricing table first because FLUX.1 does not have complete provider pricing in the local data. For the most capable/latest local choice, evaluate FLUX.1 Kontext [pro] with multimodal inputs.
