This LoRA of Sypha Belnades is trained for the Flux Dev checkpoint. It was trained against hand-captioned HD screencaps from the animated Castlevania TV series. Works well for both anime/cartoon depictions as well as photorealistic. Special attention was paid to her magical abilities and gesturing since 1) it's cool, and 2) the other Sypha LoRAs here didn't seem to accommodate that. For prompt examples check my images: https://civitai.com/user/thebollo/images. I upload all images with full metadata attached for easy import into A111 or ComfyUI.
Description
v3.0 brings a 40% increase in training data size as well as more diversity.
Instructions for example photorealistic prompt with Flux:
Checkpoint: https://civitai.com/models/161068/stoiqo-newreality-or-flux-sd-xl-lightning
Prompt: "film scene from Denis Villeneuve. Cinematography. Bright and happy atmosphere.
a gorgeous 25 year old bombshell female Sypha Belnades, sypha,1girl,Sypha Belnades,1woman,orange hair,short hair,blue robe,morning,outside,gesturing,casting ice magic, casting ice spell,windy, off white waist wrap, bloody, blue eyes"
Lora settings:
Strength model: 1.10
Strength CLIP: 1.10
Guidance: 2.5
Steps: 30
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.