Easy, Simple, High Quality (with a slight trade-off in variety)
blue_pencil-XL meets ANIMAGINE XL 3.0 / ANIMAGINE XL 3.1
License: Fair AI Public License 1.0-SD
You should share the merge recipe if you release a model merged with anima_pencil-XL.
This license does not add any restrictions on your generated images.
For more details, please see the license section of ANIMAGINE XL 3.0.
Please see the "About this Version" section for information on each version.
`No generation services` only apply to v2.0.0
HuggingFace: https://huggingface.co/bluepen5805/anima_pencil-XL
Why not merge ANIMAGINE XL 3.X into blue_pencil-XL?
I want to provide blue_pencil-XL under the CreativeML Open RAIL++-M license.
Description
# Checkpoints
# LoRAs
# Recipe
blue_pencil-XL-v7.0.0 + ( ANIMAGINE XL 3.0 - ANIMAGINE XL 2.0 ) x 1.0, Add difference(trainDifference)
[1] + ( ANIMAGINE XL 3.1 - ANIMAGINE XL 3.0 ) x 1.0, Add difference(trainDifference)
( [2] x 0.6 ) + ( blue_pencil-XL-v7.0.0 x 0.4 ), Weight sum(cosineA), Elemental: "BASE:conditioner.embedders.0:0.75,BASE:conditioner.embedders.1:0.15"
[3] + ( HoloDayo XL v2.1 - ANIMAGINE XL 3.1 ) x 1.0, Add difference(trainDifference)
[3] + ( Kivotos XL v2 - ANIMAGINE XL 3.1 ) x 1.0, Add difference(trainDifference)
[4] + [5], Weight sum(normal)
[6] + ( ArtiWaifu Diffusion v1.0 - SD-XL 1.0-base ) x 0.1, Add difference(trainDifference)
( [7] x 0.92 ) + ( AniEase v2.4 x 0.08 ), Weight sum(cosineA)
[8] + ( RAnime-XL v1.0 - ANIMAGINE XL 3.1 ) x 0.05, Add difference(trainDifference)
[9] + ( SwampMachine v2.0 - ANIMAGINE XL 3.0 ) x 0.1, Add difference(trainDifference)
[10] + ( AAM XL Anime Mix v1.0 - ANIMAGINE XL 3.0 ) x 0.15, Add difference(trainDifference)
[11] + ( Manmaru Mix XL v1.0 - ANIMAGINE XL 3.1 ) x 0.2, Add difference(trainDifference)
( [12] x 0.8 ) + ( 7th anime XL A v1.0 x 0.2 ), Weight sum(cosineA)
( [13] x 0.8 ) + ( AbyssOrange XL Else v1.0 x 0.2 ), Weight sum(cosineA)
( [14] x 0.9 ) + ( ShiratakiMix XL v1.0 x 0.1 ), Weight sum(cosineA)
( [15] x 0.875 ) + ( NeroMix v1.0 x 0.125 ), Weight sum(cosineA)
( [16] x 0.8 ) + ( Neta Art XL 1.0 x 0.2 ), Weight sum(cosineA)
( [17] x 1 ) + ( blue_pencil-XL-v7.0.0 x 0 ), Weight sum(normal), Elemental: "BASE:conditioner.embedders.0:0.8,BASE:conditioner.embedders.1:0.15"
( [18] x 0.45 ) + ( [7] x0.55 ), Weight sum(cosineA), Elemental: "BASE::0"
[19] + ( Aesthetic Anime LoRA v1s:0.1 + HaveyouWould_XL v1.0:0.25 + shadow enhancement 光影增强 v1.0:0.75 + Fixhands_anime_bdsqlsz_V1:0.5 + Anime Enhancer XL/PONY/SD v4.0:0.15 )
SD-XL 1.0-base + SPO-SDXL_4k-p_10ep_LoRA_webui:1.0
[20] + ( [21] - SD-XL 1.0-base ) x 1.75, Add difference(trainDifference)
( [22] x 0.65 ) + ( [8] x 0.35 ), Weight sum(cosineA), Elemental: "BASE::0"
( [23] x 0.9 ) + ( anima_pencil-XL-v4.0.0 x 0.1 ), Weight sum(cosineA), Elemental: "BASE::0"
[24] + ( Neta Art XL 1.0 - SD-XL 1.0-base ) x 0.05, Add difference(trainDifference), Elemental: "BASE::0"