FLUX.1 [dev] inpainting model with LoRA support. Requires an image and mask for selective editing and improvements. Warning: results are often not great.
Approx. Price
$0.060 per image
Model Type
image
Preview Examples
4
Generation controls available for this model.
Images Per Run
Up to 1
Resolution Options
9
1024x1024 (Square (1:1)), 1024x768 (Landscape (4:3)), 1024x576 (Landscape (16:9)) +6 more
Tunable Settings
7
Enable Safety Checker
Default
Yes
Guidance Scale
Default
3.5
CFG scale - how closely to follow the prompt. Higher = more adherence.
Number of Images
Default
1
Resolution
Default
1024x1024
Options (9)
1024x1024 (Square (1:1)), 1024x768 (Landscape (4:3)), 1024x576 (Landscape (16:9)), 768x1024 (Portrait (3:4)) +5 more
Seed
Default
N/A
Seed for reproducibility. Leave empty for random.
Steps
Default
28
Number of inference steps (more = higher quality, slower).
Strength
Default
0.85
Human preference benchmarks sourced from Artificial Analysis.
No Artificial Analysis benchmark data is available yet for this model.
Artificial Analysis API
A knight in shining armour holding a greatshield with 'FAL' on it
A cat dressed as a wizard with a background of a mystic forest
self-portrait of a woman, lightning in the background
Fluffy cloud castle floating in a clear blue sky cotton candy texture dreamy pastel colors whimsical
How much to transform the masked area. 1.0 completely remakes it, 0.0 preserves original.
