"Persona Fied Mix" (LJA)
Please share and post your results. I am looking forward to seeing your creations! :)
This is the end result of mixing many models to get the style I was looking for. Specifically a versitile, nsfw and sfw model for Persona characters, with detailed backgrounds and quality proportions. This is intended to be high quality persona 5 style (not the animation). It works well with The LORA's on here for all the Persona, SMT, and many anime's.
After about 100 different merge and mixes It was created as a mixture of 3 models which I find to be criminally underrated.
Please check out the 3 models which are mixed into this and rate them. IMO 5 star models.
PERSONA (HARD)
tmndMix_tmndMixVIPruned.safetensors [f27c78faa6]
Cellboxima
What's this model
"Persona Fied Mix"is a PERSONAification of Shigenori Soejima's art style and an Aesthetic I wasn't able to get with any single model. I think it is the right blend to produce some captivating images with depth, detail, and style.
The starting point for this model was my Persona Mix Hard. From there, I then added a few of the models which gave me a level of quality and a close style to the Persona one I was looking for. I tried many of the persona characters with different weights like .75, .8, 1.0 all with great results.
Using this model
Clipskip 1 or 2, with Vae-ft-mse-840000-ema-pruned.pt
with a colorful, deep, bright, clear and less semirealistic anime style. Model can be a bit horny depending on your prompt and lora's. still safe to use. I put NSFW in the negative prompt AND SFW in the prompt just in case. I always use hi-res fix and never use restore faces.
I will be very active and responsive to feedback and requests as I am currently unemployed.
Patreon is pending. Support is appreciated via
TIP:
I like to put the username in Parenthesis (LJA) when I download Lora's and models, etc. to be more organized and to find the source content again. I advise this as best practice.
I've got about 1 tb of models and it gets confusing otherwise.
Description
FAQ
Comments (11)
算是画师大模型了，味道还是相当可以的
Incredible model it does a good job without needing extra LoRa. It can be pushed to 2.5 D with some LoRa and it has a great understanding of shapes, clothes, people, anime stuff etc. Please make a XL version or Flux.
Performs very well especially considering it is a 1.5 model which sadly is all this computer/laptop can handle. Surprised at the quality and how few resources it requires to get nice results. very aesthetic and it tends to not need additional help from lora like many other models i've tried. great merge! impressive for a SD1.5 please make an illustrious version!
Thank you for your praise and encouragement 🙏 🙏 🙏 🙏
@Lja yw <3
@Lja Make more models.. it's been a long time..
@Fairing 👍
@Lja You don't post often enough. make it a daily habit!
Very good prompt adherence especially for a 1.5 model. Lightweight and high performing. Really big fan of this model. It has great backgrounds without needing lora for it, along with great composition and lighting.
Thank you it took a lot to get it to that point
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.