AniMixV9XL AnimeTV Mix.
AnimeTV/Screencap Fine-tuned Model's Based on AutismMixXL & PonyV6. 🔥
All Examples image are RAW. (TxT2Img + Hires.Fix & ADetailer).
UPDATE: Check ''MegaMixXLV3'' My new Checkpoint AnimeTV Fusion/Screencap (Based on Illustrious/NoobAI V1.1) 🔥 AVAILABLE FOR ALL GEN RIGHT NOW!
Power of this model's
Have an AnimeTV/Screencap Style. (Obs).
Capable to change a No-Character/Game Character into AnimeTV Style. (It's also Enhance/Improve some of the AnimeTV/Screencap Like Lora's into more AnimeTV).
Capable of inputting some character's name without lora's (Example: nami (one piece)/raiden shogun Booru Tags.
Pretty Good at SFW/NFSW+.
Anatomy is ''Ok'' in RAW, Easy also to Fix it with Inpainting.
Got a Big Buffer = ''Anime Screencap'' Putting it in Positive prompts = Even more Anime Screencap Style. (I Recommend).
Suggested settings
Sampler: Euler A. (LCM+ Can Work too, just lower the steps and CFG).
Steps: 20-28.
CFG: 4.5-7. (5.5 CFG = Best of both world in my Opinion).
A Good Resolution: 768x1192/832x1216.
ADetailer & Hires.Fix: Is Recommended.
Trigger Word: Anime Screencap Prompt = Buffer, (It's work without, But it's much Better with it if you want a Full AnimeTV Style).
At Beginning: score_7_up, BREAK source_anime (Combine it with Anime Screencap for Full AnimeTV Power).
Don't use negative prompts or Embedding that will deterior the Style. ([Important] Check Examples images for Negative prompts examples).
VAE: Click Here - (Better in FP16).
For Lora's/Model's Creator: It's might be a good idea to train on this model, if your character is a Full AnimeTV and your datasets is it too. (Need to test).
Otherwise i would recommend all the time to Train on the Official/PonyV6 for Full Compatibility.
This Model's have 3/4+ Of my personal Lora's trained specifically for this AnimeTV Style. (Also Added AnimeTV/Anime Background Lora's).
For the Little Story: I created it for the simple reason of: Since PonyV6/AutismMixXL was Lacking Highly in AnimeTV/Screencap Coloring without a Lora's and Even with them sometime the Style was not Consistent.
It was a Challenge also to have the advantage of PonyV6/AutismMixXL (Anatomy, Booru Tags, ect) And to work full without a Trigger Word (Yes because Pony is Not very good without, It's not like SD 1.5/SDXL, you need to hard train a Lora/Put more Weights, This model's taked me Many Die & Retry to create ahah), Now he work without AND have a Buffer with ''Anime Screencap'' Prompts.
Also i'm pretty Satisfied to be the First RAW AnimeTV/Screencap Model's on PonyV6.
More Update's coming it in the Future.
PS: Don't hesitate to post your Artwork/Image, I like to see what Other People's create with My Model's. (It's also help to popularize AniMixV9XL).
PS2: If you merge it into a Model's, @ me on your Model's, or Talk to me in private.
Description
AniMixV9XL-V2 - Big Update:
In this new Version, AniMixV9XL-V2 is now more better at:
A little bit better at Background + NOW Powerful at Effect/Particles (Aura) ! (Added more Datasets to it).
Even more Diversified in Gender, More facility to do Male Character's. (Added also Datasets for it).
In someway better at Hands (and Feet), SFW/NFSW is a little more consistent + Muscular/Abs more Easy too.
A little more Anime, even without ''BREAK source_anime'' prompts.
For Jojo's/One Piece/Dragon Ball Z Fan (Specially Jojo's, Less Other's), The model's have facility to do these Character's and their Style !
A little bit more Better compatibility with Lora's. (Enhancing also even more AnimeTV Like Lora's).
FAQ
Comments (9)
Definitely will try it, is there a list of innate characters in the model?
Yes! Since i Fine-Tuned it From AutismMixXL/PonyV6 He keep's Many booru concepts tags, so character's who worked on the other, Will also work here with it.
Otherwise since i added Datasets for Background/Effect/Particles & Male Character's, Some now are Innate to V2 Ver EX: Jojo's Character's + They also keep their Style, He also have some Data's Now for OP & DBZ but less than Jojo's too.
Is a VAE baked in or do we need the SDXL one?
You need this one: https://civitai.com/models/140686/fix-fp16-errors-sdxl-lower-memory-use-sdxl-vae-fp16-fix-by-madebyollin (It's the default one atm, like i suggested in Recommended Settings).
This is great - thanks!
Update3-13/07/2024: AniMixV9XL-V2.5/REV is Now out. 🔥 | Click About this version for More Info's. 🔥
Clearly satisfied about the result. (The best Checkpoint i created to this day).
Read Description on How to use it & Also to use like in my suggested settings & Also ''Anime Screencap'' Prompts if your Character's come from a Game/NoAnimeTV Character's.
I'm enjoying this checkpoint a lot giving me the results I usually want since EDGpony. Keep up the good work and hoping to see more updates in the future!
Thanks for your support ! The next version AniMixV9XL V2.5 Will come soon and fix the problems of V2 atm (Less Pixelization, Better Hands/Feet even without Hires.fix + Far more Stable/Better compatibility Lora's), He will be really good.
PS: Don't hesitate to post your Generated Image/Artwork, I like to see what people create with my model's !
@KXRO of course. i plan to use this as my main checkpoint for the time being so expect more cross postings
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.