NoobAI/illustriousXL/Animagine Stabilizer
This LoRA can make the character pose and style more stable. Including face, eyes, hands, overall details, automatically balancing brightness and contrast, ...many things...
Recommended strength: 0.4~0.8.
Recommend lower your CFG (-20%) after apply this LoRA.
Version prefix: nb_ep11 = NoobAI e-pred v1.1. illus = illustriousXL v0.1, ani40 = Animagine XL 4.
All cover images are generated using the base model in sd-webui with default settings, no negative prompts, no artist or style tags, no other fixes,no rescale cfg, etc.
The training dataset contains ~1k hand-picked images:
Character-focus. (The characters take up most of the image. I also cropped and rotated many images if necessary.)
Clear characters. (Clear character lines, hands, faces, eyes, no obstruction, no blur effect, etc.)
Natural poses. Natural body proportions. (No exaggerated art, chibi, jojo pose, etc.)
High quality and full of details.
Plus a little bit everything, landscape, furry, animals... to balance the dataset.
Unlike concept/strong style LoRAs. This LoRA was not overtrained. It will not dramatically change the model output.