The purest Faye Valentine (Cowboy Bebop)
I made a video on how to achieve the same quality or just repeat my art
P.P.S. new model ogipote (2.5D) and ogipote (2.5D)_v2.0 on Boosty
The first lora where I did the preprocessing right away, and not after several versions. With the help of neural networks, I improved all the art, removed the background noise, removed watermarks and other elements of the text, except for the background, made a complete selection of prompts manually! In the end the result was worth it) The purest art.
Thanks to the high quality of the images, you can achieve detailed backgrounds in the same style, which was not in my past works
LORA weight from 0.2 to 1 depending on your goals, 1 - closer to the original style, there are no restrictions here. I use 0.6-0.7
CFG Scale - 3.5-5 (According to my personal observations, 4 is the best choice)
Use model Abyssorangemix3aom3_aom3a3.safetensors
just use hires fix as much as your video card is capable of, so as not to give an error, with 8gb of video memory it is 512x768 with hires fix 2, upscaler Latent (nearest-exact) or just Latent (if there are problems with the image), the picture will be much more detailed.
Trigger Words: Faye Valentine
Combined with my other LORA
How to use LoRA's in auto1111:
Update webui (use
git pulllike here or redownload it)Copy the file to
stable-diffusion-webui/models/loraSelect your LoRA like in this video
Make sure to change the weight (by default it's
:1which is usually too high)
*Information taken from Lykon
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
Use model abyssorangemix3AOM3_aom3a3
P.S. If you want to support me, then you can subscribe to my Patreon and get builds earlier than they come out here (versions on patreon will always be newer by one than here) This will help me a lot in updating the video card over time to make models even better and faster (the main thing is better)
FAQ
Comments (12)
How do I reproduce the first image? I used the same model and the same parameters and yet I got a different imange :(
probably used controlnet, try to do the same
@Agneel Thanks!
@LupinSensei if you use xformers, it will not work exactly like this, but everything is quite simple here, I use the standard Eta noise seed for convenience - 31337
@LupinSensei as far as I remember here 512x768 with hires fix 2, upscaler Latent (nearest-exact). I never use controlnet and img2img, it's a bit of cheating in terms of showing what lora can do c:
Cool, but how hard would it be to build a larger model, possibly checkpoint for specifically 1995 Evangelion series? I searched entire civitai and there is nothing like it.
It's not my priority right now, but I'll think about it)
@OneRing I think it should be done like this one here with studio ghibli style: https://civitai.com/models/6526/studio-ghibli-style-lora not just focusing on characters, but spaces, scenes, areas, robots, monsters. Just to fully capture style of series. The Evangelion 1995 series are super popular, so I think many people would appreciate that.
@Werry I can do better and in general I love evangelion, it's just that there are priorities right now to update my old work, plus i'm very busy with forced relocation, otherwise it's a good idea, i'll consider it
@OneRing Thank you!
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✧
I restored my PATREON (or rather created a new one with the permission of patreon), if someone wants to support I posted there all my new models and LORAs, which were paid on BOOSTY in one archive. I will be glad if you even subscribe to patreon for free, I will know that you care about my work and you want to see updates.