Simile = comparison, likeness, parallel, similar, resembling
Note: Preview images are generated without the use of LORAs
NoobAI ver. [v3.0, v4.0, v5.0, v6.0]
⚠️ATTENTION⚠️
Check 'about this version' tab for more details..
Also, here is the list for the artist tags. There are two files in the zip file, one if the full artist list and the other is the list of artist that I've personally tested to be working and most of them are also from gay artists..
About
To be honest I didn't expect to update this quickly but I can't resist NoobAI's updated datasets. Artist tags also performs much better with less dependent on emphasis to achieve a desired effect. Overall it is an improvement of the already great model, Illustrous XL.
Tips for artist styles / characters
Similar to ILXL, just add in the artist or character tags and that's it. If you're not sure what to write for the tags, just search it on danbooru or here. See sample images for examples on how to prompt the tags..
My Settings
Sampling Method: - Euler a (less detailed and smoother textures)
- DPM++ 2M (more detailed lines and textures)
Sampling Steps: 20+
Upscaler: 4x_NMKD-Siax_200k / Remacri
CFG Scale: 3 - 5
Clip Skip: 2
VAE : Already built-inPositive Prompt:
very awa, masterpiece, best quality, absurdres, perfect quality, detailed background, intricate detailsNegative Prompt:
lowres, worst quality, bad quality, bad anatomy, signature, username, logo, watermark, artist name, bad handsIllustrious ver. [v2.0]
About
Personally I still prefer the default style of the Pony version but the prompt adherence and style flexibility of the Illustrious XL is just too good to pass up. Prompting and tagging is also a lot easier than the pony version from what I've tested. I tried to replicate the look of the Pony version but there's just too much artist styles for me to do anything without messing with the overall quality, oh well..
Tips for artist styles / characters
Illustrious is a fine-tuned model trained on Danbooru datasets, so there are a lot of data on various artist's styles and characters. So you can prompt a specific style or characters without the need of loras as long as they have substantial amount of dataset on Danbooru and are not too recent. See sample images for examples on how to prompt styles..
My Settings
Sampling Method: Euler a, DPM++ 2M / DPM++ 3M SDE
Sampling Steps: 25+
Upscaler: 4x_NMKD-Siax_200k / Remacri
CFG Scale: 3 - 6
Clip Skip: 2
VAE : Already built-inPositive Prompt:
masterpiece, best quality, absurdres, newest, perfect quality, best quality, absolutely eye-catching, detailed background, intricate detailsNegative Prompt:
lowres, worst quality, bad quality, bad anatomy, sketch, jpeg artifacts, signature, watermark, artist name, oldPony ver. [v1.0]
About
Just like with my HomoSimile model, I'm trying to get that specific look that's between 'anime' and 'western art'. I went a bit easy with the LORAs to ensure better compatibility with other styles. So if you want to use a specific artist's styles it wont diminish the results.
My Settings
Sampling Method: DPM++ 2M / DPM++ 3M SDE
Sampling Steps: 30+
Upscaler: 4x_NMKD-Siax_200k / Remacri
CFG Scale: 4 - 6
Clip Skip: 2
VAE : Already built-inPositive Prompt:
score_9, score_8_up, score_7_up, highly detailed, intricate details, detailed backgroundNegative Prompt:
score_6, score_5, score_4, score_3, score_2, score_1, low quality, deformed, bad hands, watermark⚠️DISCLAIMER⚠️
Please do NOT generate illegal content with this model. You are solely responsible for any unethical use of this model(s)
Model License
Description
FAQ
Comments (33)
Simile after Fidelis does it mean Veritas is next?
Honestly? I'm not sure. you can get pretty decent 2.5D images with most pony models with the right lora so it feels a bit pointless for me to make it..
@Kairen92 Yeah that's true but I think the Verita style is still unique enough to stand out
@SquarePandaHead I'll think about it, lol..
You are doing god's work, look at those milkers
lmao .. 😂
Your models are all soooooooo good, thank you for all your creative energy and ongoing contributions! 🙏🏻❤️🏆. I was wondering why they not on the Civitai generator?
Keep it up! More male-focussed work is very well appreciated and needed
Thank you so much! ❤️
Well apparently its up to Civitai if they want to host a model for their generator or not. I already sent them an email about it but still haven't gotten a reply. Probably too busy hosting yet another female-focused model.. 🤷
I'll let you know if anything changes..
@Kairen92 Did you try get hold of the guys on Discord? Your models are better than a lot already on the generator!
@m900100 They actually replied to my email today. They said something about not having enough storage so they are "unable to manually add new checkpoints to the Generator at this time". 😑
They said they might be able to replace my SD1.5 HomoFidelis model in the generator with the pony version and that's about it. I did told them if its possible please add the HomoSimile model as well but I don't think that's gonna happen anytime soon, not unless they suddenly upgraded their server storage..
@Kairen92 Wow, how disappointing. New checkpoints, Lora etc are added everyday. Almost feels homophobic. I thought Civitai was more open minded than that. Let's hope it is simply a storage issue and in time all your models will be available 🙏🏻
@m900100 Hmmm, it is what it is. I guess its also my fault for not putting an anime girl with big tiddies on the cover lol..
Oh my god, I wish it's on tensor art.
I'll upload it there later lol ..
I haven't played with it much, but I've enjoyed it a huge amount so far! ...also, that's probably what she said. Great model though!
Lmao, I hope it's good enough for you to enjoy (that's what I usually say 🥲)
Oh,we can use HomoFidelis Pony with on-site generation now,maybe HomoSimile Pony will be on the Civitai generator later.
Hmmmm, unfortunately no. For whatever reason Civitai only allows me to have only one model on the on-site generator. They even took off HomoFidelis SD1.5 to make room for the Pony version..
You're always working hard making such incredible models, thank you so much for sharing these!!! Your Homo-X series of checkpoints are unmatched :D
Omg thank you so much. You're too kind .. 😭
can you set to be intended to produce mature themes so we can generate on civitai?
I don't know if that's gonna do anything. I already emailed Civitai about it and they'll only allow 1 checkpoint model from me. This site is basically dominated by female content so they don't really care that much about male related stuff since there isn't as much demand for it.. 😔
@Kairen92 oh ok
When generating, you only get 1 result among the models you search for homo and gay, and that is this one. and it does not give realistic or satisfactory results.
Well, I think this model is meant for illustrative styles, more than hyperrealism.
i didnt mean hyperrealism. just a acceptable to satisfaction. just a normal types.
This model is not available for generating on Civit. You must have it confused with homofidelis which does actually provide semi-realistic to realistic results if you are using it properly. Homo-simile is not meant to be realistic so commenting on here about realism isn't gonna get you much mileage.
The colors are super vibrant and natural, and the skin texture looks amazing. The way it handles clothing folds is seriously impressive too, which isn’t something you see often. Overall, it’s such a solid and reliable checkpoint!
Thank you so much !!
Onsite civit generation/remix soon?
Hmmm, not sure. It depends if Civitai allows it..
@Kairen92 but how can i generate ai arts with your checkpoint?
@starkomi20 You can try TensorArt, some of my models are also available there. Or you can run in locally on your own device..