Art style based on えぶるぃ (@everyntrge) (https://ci-en.dlsite.com/creator/2935)

v2 Release Changes:

• Removed some old training images for consistent art style

• v2_AnimagineXLV31 is trained on Animagine XL V3.1 (https://civitai.com/models/260267)

• v2_PonyDiffusionV6XL is trained on Pony Diffusion V6 XL (https://civitai.com/models/257749)

• v2_AnythingXL is trained on Anything XL (https://civitai.com/models/9409/or-anything-xl?modelVersionId=3842??)

v2 Training Parameters:

• 213 images with Repeats of 8

v1 Release:

• v1_AnimagineXLV31 is trained on Animagine XL V3.1 (https://civitai.com/models/260267)

• v1_PonyDiffusionV6XL is trained on Pony Diffusion V6 XL (https://civitai.com/models/257749)

v1 Training Parameters:

• 389 images with Repeats of 4

• Batch size of 5, Epoch of 5

• Learning rate of 0.0003

• Network Rank of 32, Network Alpha of 16

• Clip skip of 2

• No regularisation