Since the release of Anymagine XL 3.0, there is no need to update the model.
1.32 is the last update.
The Anymagine XL 3.0 is superior to this model.
version 1.3
I extracted LORA from previously merged models and added LORA and lycoris that I learned before to increase tag accuracy.
(kohakuXL extract + DPO extract + LORA learned personally + hassaku extract)
version 1.21
Deephentai-mix-v1.2 (This is a different model than the test version.)
+
Version 1.21 merges BluePencil 2.0.0 and block tuning to improve stability.
Version 1.0 was released for about a month with no consideration for stability.
just focused on merging a lot of information.
Because of this, it was very unstable.
The 1.21 model is a compilation of models created by people much better than me,
compensating for weaknesses in my model with block tuning,
and merged in other additional LORAs.
It is still being worked on for stability and tag compatibility.
I recommend my embedding
I recommend the default VAE.
positive: 2 or 3 big tags like style, fonts, etc. + 1 sentences describing the situation
Too many sentences can rather damage the image.
Intuitive and consistent tags and 1-2 clear sentences are optimal.
negative:
text, watermark, negative, negative_v2, negativeXL_D
It is a model that merged several checkpoint models and learned Lora after learning it.
(hentaiMixXLRoadTo_v21+_hassakuXLSfwNsfw_alphaV09-sdXL_v10_x0.5.fp16+ssd-1b-dalle-3-step00077700.fp16 + (kohakuXLBeta_beta7Pro+_reproductionSDXL_2v12-sd_xl_base_0.9-fp16_x0.25.fp16+ssd-1b-dalle-3-step00077700.fp16 - sd_xl_base_0.9-fp16) x 0.2) x deephentaiMix_v40_Stableversionx0.775+envyagendaxl02_v10x0.225.fp16 x 0.75 + bluePencilXL_v200 x 0.25 x deephentaiMix_v50 + (hentaiMixXLRoadTo_v3025DHCNSFW - sdXL_v10) x alpha(cosine) + Merge with Lora personally made
Description
FAQ
Comments (5)
i am really impressed! this checkpoint has the same quality in sdxl like "something" in sd.
i really like it!
now, "something" got a big brother :D
EDIT: sorry for this double-upload. civitai has some very annoying hiccups at the moment and uploads appear or disappear the whole time. and i just can't figure out the reason, but i can't delete anything.
I'm fine
found out some very funny pattern about this checkpoint that can be insanely useful:
for my images, i mainly use "realistic-shot and 4k" to generate realistic images in high quality. and the pattern i mentioned is, that, every time, this checkpoint doesn't understand a prompt or doesn't want to generate the prompt i used, it switches back to flat-anime-colors.
with this pattern in mind, i get to test many new prompts that i will create in the future
found 2 very heavy prompts for realism for this and other checkpoints:
in positive: (professional-photo-realistic-quality)
in negative: anime-realistic
anime-realistic was more or less a fun idea, but it is super heavy to be honest.
I'll keep that in mind.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.