This series of the models was started (v0.4) from DucHaiten-Pony-Real (beta) by DucHaiten.
Version v1.0 was trained using a LoRa mode in One trainer. Next version are trained in Fine Tuning mode (full SDXL training).
Up to v1.0: Photorealism, lighting and anatomy related LoRas from CinEro series are integrated into this model in order to amplify cinematic render.
Goal of training was to improve to stability of anatomy and make the picture more realistic and moody / cinematic.
Version 1.1: shifted to fantasy / sci-fi themes with less realistic and more contrast / unstable rendering.
Version 1.2 [SOON]: is v1.1 further development with shift to horror / tentacles theme.
PS: be responsible and don't abuse this unrestricted model.
Description
Improved detailing, contrast, face rendering, poses, natural background (forest, mountains).
Follow me an look into the prompts I am using in posted images for particular phrases.
FAQ
Comments (17)
Can we have some more and varied samples before I shell out buzz for this?
Of course.... I'm in progress with it. Suggestions are welcome.
Oh I'm easy, but feel free to steal any of my prompts - I don't do NSFW but have at it if that helps :)
https://civitai.com/images/23337715
@_REME_ Please find the image produced with your prompt adapted by Omost application.
I just used your prompt as an input to Omost. It converted your prompt into the canvas instruction (look at image metadata). Then I used this instruction in ComfyUI (workflow with T2I + UltimateUpscaler).
Result is not awesome but OK to me.
@homoludens I missed out on the early access period, but I think I still sent you the 500z, let me know if not
@_REME_ I see the Donation 500 in ring bells... TANK you ALOT!!! :D
@_REME_ Community made me big donation... The problem now..... I NEED TO COLLECT ALL MY GOOD PHOTOS AND BUILD SOME HUUUUUUUGE DATASET TO SPEND ALL THIS BUZZ ON TRAINING :D
@homoludens worst problems to have ;-)
@_REME_ it can be funny for someone... but for me it is hugillion tons of work on captioning all the images XD
I don't see a lot of men in the gallery. Can this do men, including nude ones? Or are the improvements just on the female form?
it should be capable of... I'm just not too interested in drawing handsome unwomen ;)
we can try
https://civitai.com/images/23393763
"like this you like, Jedi?" (Yodium Chloride)
@homoludens That is absolutely terrifying!
I love the light in all your models, it's inspiring of one of my models, great work as always
watch propmpt (nearly all images)
"score_9, score_8_up, score_7_up, source_cartoon, rating_safe, realistic breast level photograph, motion blur, furious movement BREAK The photograph shows..."
what do you want cartoon or realistic? :D
It just a quick copy of other user's prompt with additions....
No real purpose of this combination, I believe.