FLUX.2 [klein]
Inspect the documented capabilities, access conditions and sources for your task.
Initial research: 2026-09-21. Check current terms before choosing.
Automated fact checks · 8 fields
AI extraction with a second evidence validation pass. These dates apply to the listed fields.
- Open weights · 2026-10-10 · Source
- Edit an existing image · 2026-10-10 · Source
- Include text in images · 2026-10-10 · Source
- Keep characters consistent · 2026-10-10 · Source
- Use outputs commercially · 2026-10-13 · Source
- Commercial use · 2026-10-13 · Source
- Commercial terms · 2026-10-13 · Source
- Commercial source · 2026-10-13 · Source
Updated
The facts
- Version
- 2 (klein)
- Price
- $0.014 per image. Usage rate. Settings and included usage can change the charge.
- API
✓Supported - Open weights
✓Supported - Commercial use
- Commercial use available under tiered licensing (Builder, Platform, Enterprise, etc.); Builder tier limited to single domain, not for client/downstream use; permissive commercial use only in Enterprise tier
- Text rendering in image
?Not verified No explicit text rendering capability mentioned in source passages
Source for Text rendering in image (opens in a new tab)- Image editing/inpainting
✓Supported Unified generation and editing: text-to-image, image editing, and multi-reference support in a single model
Source for Image editing/inpainting (opens in a new tab)- Character consistency
~Partly Multi-reference generation supported, allowing combining multiple input images and blending concepts
Source for Character consistency (opens in a new tab)- Commercial licence
~Partly Commercial use requires a paid license; Builder tier restricts to 1 domain and internal use only; Enterprise offers permissive commercial use; tiered restrictions apply throughout
Source for Commercial licence (opens in a new tab)
From the publisher
Automatic source checks. These do not change the verification date of the facts above.
Sources
Beyond feature support
Quality evidence.
How well a model performs depends on the task, version, and settings.
We have not published a reviewed quality evaluation for these versions yet. Feature support and price do not establish output quality.
Try the same small task with each option. Compare prompt adherence, text, detail, and consistency.
Check the exact version and test setup. Results on one task do not establish quality on another.