weight 0.7 is best.
☆Very important
swap
blue eyes ↔ black blindfold, covered eyes
black dress, black skirt ↔ covered navel, (white leotard:1.2)
outfit A (blindfold, dress)hm2b, black blindfold, covered eyes, mole under mouth, clothing cutout, long sleeves, puffy sleeves, juliet sleeves, feather trim, black thighhighs, black gloves, black dress, black skirt
outfit B (blindfold, leotard)hm2b, black blindfold, covered eyes, mole under mouth, clothing cutout, long sleeves, puffy sleeves, juliet sleeves, feather trim, black thighhighs, black gloves, covered navel, (white leotard:1.2)
outfit C (without blindfold, dress)hm2b, blue eyes, mole under mouth, clothing cutout, long sleeves, puffy sleeves, juliet sleeves, feather trim, black thighhighs, black gloves, black dress, black skirt
outfit D (without blindfold, leotard)hm2b, blue eyes, mole under mouth, clothing cutout, long sleeves, puffy sleeves, juliet sleeves, feather trim, black thighhighs, black gloves, covered navel, (white_leotard:1.2)
lora Ver.2
144MB → 36MB
Remove low-quality datasets
If you use this LoRA in a reality model (Checkpoint), it may not be perfect.
Description
FAQ
Comments (4)
Can you add the machines from the game as well? or is there already something out there, or similar?
Do you mean Pods? I think it would be problematic to merge them with the character and have them learn at the same time.
I think it would be best to create separate LoRAs for 2B and Pods to be on the same screen.
How come your sample photos use a different lora?
where is that one?
@TheCyanHawk When I upload the file to Civitai, the file name changes. It is actually the same LoRA.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.