This Illustrious based checkpoint merge produces 2D Anime pictures with a clean and detailed style.
It is the result of merging 2 of my current favorite anime checkpoints.
Update
V-pred V3.0
This release features a cleaner anime look with vibrant colors. The anatomy and prompt adherence also improved and additional models were added to the merge.
For best results, the following quality tags are recommended:
Positive tags
masterpiece, best quality, absurdres, highres, very aesthetic, high quality, detailed, insanely detailed, beautiful, very awa, anime screencap
Negative tags
lowres, bad quality, worst quality,bad anatomy, sketch, jpeg artifacts, ugly, poorly drawn,blurry, transparent background, censored, (simple background:1.6), artist name, signature, watermark
V-pred V2.0
Made some improvements to to the style and prompt adherence and added an additional model to the merge.
V-pred Version 1.0
This a Noob AI V-pred based version of Hotaru Blend. It is still work in progress and the style is not yet where I want it.
But it is already working very well. It has a good prompt adherence and results are reproducible to some degree.
Recommended settings:
Sampler: Euler A + SGM Uniform or DDPM + Align your Steps
CFG: 3-5 (I prefer 3.5)
Steps: 25
merged models
copycat-noob obsV1(vpred)
hikariNoobVPred_121
CocoaMix style Yume (Illustrious) v-pred V2 (in V-pred V2.0)
chromalinemixNoobaiV_40 (in V-pred V3.0)
cocoamixYumeIllustrious_v50 (in V-pred V3.0)
raehoshiIllustXL_vpredV10 (in V-pred V3.0)
+ additional styling loras
Version 4.0 DMD2
This release is the same model as Version 4 with an additional DMD2 lora merged into for faster image generation. The quality is nearly identical to the main model, except that this version has a bit more saturated colors.
Recommended settings:
Sampler: Euler A + SGM Uniform
Steps: 8-12 (recommended 10)
CFG: 1.5 - 2 (a bit higher should also work)
Version 4.0
For this version I added an additional personal merge model which