For this model, I have set out to depict typical anime appearances of the newer generation with a touch of realism, without compromising the character's style. It was also a priority for me to ensure a diverse range of colors.
Furthermore, this model is well-suited for depicting explicit content.
__________________________________________________________________________________________________
Recommended parameters:
((masterpiece)), (best quality),
Negatives: (worst quality, low quality:1.4),
Sampler: Euler a: 20 to 30 steps.
Sampler: DPM++ SDE Karras: 20 to 30 steps.
Sampler: DPM++ 2M Karras: 20 to 30 steps.
Sampler: DPM++ 2M SDE Karras: 20 to 30 steps.
CFG Scale: 7 to 12. Recommend: 8
Resolutions: 512x768, 512x1024 for Portrait!
Resolutions: 768x512, 1024x512, 1536x512 for Landscape!
Hires.fix: RealESRGAN_x4plus_anime_6B, with 20 steps at 0.5 - 0.6 denoising, upscale 2.0.
Clip Skip: 2
Eta noise seed delta: 31337
Textual Inversion
__________________________________________________________________________________________________
Bad-Hand-5
https://huggingface.co/yesyeahvh/bad-hands-5/tree/main
NegfeetV2
https://huggingface.co/qdas/negfeet/blob/main/NegfeetV2.pt
VAE
_________________________________________________________________________________________________
kl-f8-anime2.vae
https://huggingface.co/Norisuke193/kl-f8-anime2/blob/main/kl-f8-anime2.vae.pt
vae-ft-mse-840000-ema-pruned
__________________________________________________________________________________________________
Base of Danbooru
Description
I have merged it with various other models and integrated some elements, including hands, that contribute to the overall improvement. This represents the final update and consequently the final version.
FAQ
Comments (16)
pruned version plz
online in the next hour :)
what happened to Sakushi-Nova (97295), it seemed different from this SakushiMix, and wanted to understand what is the difference in that one. Thanks for a great model :)
This model was a failure. I have experimented with Loras and was curious about the effects. But I've made progress in dealing with it! New checkpoints will appear soon
No male
Why am I not able to reproduce the same results even though I'm using the exact same settings?
Why are my results less colorful/vibrant than the examples? Is it related to the "unavailable" model I can't download?
It's the embeddings. Open the details and download the "kl-f8-anime2.vae" and/or "vae-ft-mse-840000-ema-pruned" files.
@canyouread7 Doesn't work with them either
Edit: Older versions seem to work, just not newest one.
@pihlawrkr738 hello, how what version did you install? and where do you put the file?
I upgraded from 2.0 to final and it got very hazy.
i get a grey film on generated images with the final version, too.
Really Good Model, im using this model mostly for generate image. Thanks for a Good Work 🙏
@canyouread7
Hi, will you please bake your vae into Final? I use Mage Space and there isn’t support to add vae yet.
Dude, your model won't let me train my LoRA that I'm doing now.
A very cool anime model! Good anatomy, great flexibility and responsiveness, and a nice cartoon style. Super! Thanks!
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.