Anime Screencap Style
NEW ERA v1.0 (SDXL / PONY DIFFUSION version combining almost all my popular models with an emphasis on retro anime)
P.P.S. new model Anime Screencap / LORA / PONY DIFFUSION and NEW ERA 3.0 (MODEL) PONY DIFFUSION / SDXL on Boosty
I made a video on how to achieve the same quality or just repeat my art
P.S. version 1.5 (2.5 times more dataset, more NSFW, more details and better quality) on Boosty
P.P.S. new model ogipote (2.5D)_v3.0 and ogipote (2.5D)_v2.0 on Boosty

version 1.4 is an attempt at high widescreen resolution, there should be less distortion, but this is not a panacea
From the name it is clear that the model is designed to implement screenshots extracted from the anime. Why a model and not Lora? I still think that the model is more versatile and gives much more "correct" results, and frankly the model is capable of better quality than Lora. However, I do not deny that I will make Lora according to this model, if there is interest.
VAE is embedded
negative promts: (worst quality, low quality, extra digits:1.4) or (worst quality, low quality:1.4)
Eta noise seed delta 31337 (if you want to repeat the art)
Trigger Words (prompts):
anime screencap
anime coloring (optional)
almost all the art is made on a hires fix with the following settings: upscale by 2, Denoising strength 0.57 - 0.6, upscaler latent (neares-exact), the original resolution is 512x768 or 576x832, or 640x960
CFG Scale - 5 (it's very important guys, I noticed many people use 7 by default, they don't need it, since vae is built in, then on 5 the image turns out juicy, no more is needed. In addition, the hands and proportions are obtained better by 5 and the characters do not look like "overcooked chickens")
Please post your work with or without comments, it will help me improve. Thanks!
If you like my work, click on the heart above, I will be pleased :3
Description
approximately doubled dataset. Changes:
1 Deeper colors
2 Improved widescreen images
3 Slightly improved eyes
4 More styles
5 Slightly better in nsfw
6 Better backgrounds
FAQ
Comments (8)
Why clipskip 1? I thought those anime tags are meant for clipskip 2?
in fact, without going into details, there is simply no need for this for a long time, it was a novel ai problem, but modern models have little left of it. The loss of the layer increases diversity, but reduces the correctness of the output data, which is essentially just an add-on now if the model did not come out quite well or the author of the model does not know what he wants to achieve. I know how many epochs I need, how many steps for a particular model and have been "cooking in this business" for a long time, I don't need to use clip skip 2 to get the best results. Diversity can be achieved for a long time by other methods than skipping a layer. The fact that most creators use clip skip 2 is rather information about it, which has been for more than a year, that it is better to use clip skip 2 for anime models, but now again, I repeat, there is no need for this with the correct configuration of the model
That's some useful info about clip skip. Just out of curiosity, which model did you use to train this checkpoint?
Is this model only capable of outputting anime screenshots like sections of animes it was trained on or is it capable of creating characters on the fly too?
Hello! I am interested in merging this into one of my models and i know it says no merges allowed, but i'm wondering if it would still be okay, i understand if you say no.
yes, you can merge this model with your own
Patreon deleted my account for very ambiguous things that I disagree with, but if someone subscribed to me for about the last month, everyone should have been refunded, because I haven't withdrawn money from patreon for a long time, I will try to make a new account, but as patreon support wrote to me, I first have to get their "approval" otherwise the account will be deleted again.
I had to create a new page, already on boosty, because patreon deleted my account and does not allow me to create new accounts in the next two months. I posted an archive of all my loras and models from patreon on boosty. I hope you will support me in this difficult situation and subscribe (If you can't support me, then subscribe for free and stay tuned for updates on my work, thanks to everyone who responds), the amounts converted into dollars here will be slightly lower than in the old patreon, I love everyone! (ノ◕ヮ◕)ノ*:・゚✧
Details
Files
animeScreencapStyle_assV13.safetensors
Mirrors
animeScreencapStyle_assV13.safetensors
animeScreencapStyle_assV13.safetensors
animeScreencapStyle_assV13.safetensors
animeScreencapStyle_assV13.safetensors
a.safetensors
a.safetensors
BILEKASS.safetensors
animeScreencapStyle_assV13.safetensors
animeScreencapStyle_assV13.safetensors
animeScreencapStyle_assV13.safetensors
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.



















