This LoRA was trained on approximately 15 images of Gal Gadot, initially upscaled using SUPIR Upscaler. This is a variant of the other published model, with less facial similarity but greater body similarity. It also boasts improved aesthetic and visual quality (better handling of light and composition) and reduced noise (trained on images refined to eliminate input noise). One drawback is the hands – they aren't as consistent as in the other published Gal Gadot model, but the coherence is still acceptable, not terrible).

For optimal use, I recommend the following settings:

• Sampler: Heun

• Scheduler: Beta

• Steps range: between 20 and 50.

• Strength guidance: 3.5

This LoRA exhibits high text adherence and versatility in facial expressions. I recommend using the exact same input for the CLIP L text encoder as for the t5xxl text encoder; I've conducted dozens of tests, and it performs better with longer text prompts.

The LoRA's style is primarily realistic, with strong compositional capabilities. I have trained another LoRA (with 15 images) that I consider superior to this one in terms of aesthetic and visual quality (in all tests using computer vision models, the other LoRA, which I'm not releasing, consistently scored higher in aesthetics and quality). However, I won't