AAM XL Anime Mix
Anime Screencap Style Model
Do you like what I do? Consider supporting me on Patreon 🅿️ or feel free to buy me a coffee ☕.
A ❤️, a kind comment or a review is greatly appreciated.
Join my Discord Server
This is essentially derived from AAM AnyLoRA Anime Mix, but it's based on SDXL.
It won't work with loras and embeddings for SD1.5 even if they're trained on the original AAM or AnyLoRA. "Mix" as in mix of anime styles.
I suggest you use CFG 5-7 (not higher than 8), 20-30 steps with Euler a.
Upscalers suggestions are None (bicubic upscaling in comfyui), any good GAN for anime or Latent (only if you know what you're doing).
For Turbo I suggest you use CFG 3-4 and 8 steps Euler a or 15 steps LCM.
Unlike with DreamShaper Turbo, I think base AAM XL is better than AAM XL Turbo most of the time. However the latter is MUCH faster.
Purpose of this model
Make amazing anime style artworks on its own.
Train character loras.
Use anime styles.
Generate anime art and stylized art.
It can generate hentai on its own, but you might need loras and embeddings for specific stuff.
ComfyUI Workflow: https://pastebin.com/BHCEzc6T
Finetuned over "DreamShaper Anime", which is a mix of Anime Art Diffusion, Hassaku and DreamShaper XL. Finetuned using the AAM dataset. Fair AI Public License 1.0-SD
Description
For Turbo I suggest you use CFG 3-4 and 8 steps Euler a or 15 steps LCM.
FAQ
Comments (9)
When you say "For Turbo I suggest you use CFG 3-4 and 8 steps Euler a or 15 steps LCM"
what do you mean by 15 steps LCM? IS there any LCM thing I have to install?
LCM is a sampler, used a lot for the animated diffusion stuff. I've never used it personally but specifically LCM models tend to be a bit faster/lighter to run so preferred for that kind of thing.
@Art3mas yep, LCM is a super fast sampler, but has lower quality compared to the other ones.
Was this train on Booru style tags by chance like NAI? I'm curious because I've been using those type of tags and the model seems to follow them really well. Which is a good thing for me!
Both XL text encoders will understand booru tags like they do understand human language. Keep in mind even NAI had SD1.4 text encoder, untouched.
@Lykon That makes sense and explains why those tags work well. Thank you for this checkpoint!
feeling dumb, hoping someone can help out. All the images I make are fragmented and split, tried changing negatives, tried removing the few loras I was using, nothing...always split, anything I'm doing to invoke this or is it a graphics card issue :/ https://imgur.com/a/V58RFDR
seems like you're generating the 1st pass at a too high resolution. Don't go lower than 768 and don't go higher than 1100.
try changing resolution
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.