~ Please upload your creations and give the model a Thumbs Up if you liked it. It means a lot! ~
All versions have different recipes and flavor. Newer does not mean better!
A NSFW NoobAI XL Epsilon-pred 1.1 based model that produces photoreal images with much greater flexibility and scene composition prompt adherence than any other photo/real models I tested so far, including realistic pony models.
v0.3 Contrastes
Produces "realistic" images.
Added CyberIllustrious, IllustriousSat-IOR, 1girl printer 2.0, to the mix. Still NoobAI EPS 1.1 based.
v0.2 SummerBreeze
Produces "realistic" images.
Reworked the merging concept and reduced realism by ~20% to improve prompt adherence and image stability.
v0.1 PhotoReal
Produces photoreal images.
It is by no means perfect. As a child of a photoreal SDXL model, it will generate extra hands and bad eyes sometimes. Rarely, it may require ADetailer to fix faces for people in the distance.
And it is very naughty. :D
Same with my real Illustrious merge - ILove, I wanted to create a model that understands booru tags, knows (some) concepts provided by the amazing Noob-AI XL and produces photoreal images. In other words, I wanted a NSFW SDXL model that would provide greater adherence to complex prompts from scene composition perspective.
The complex multistep (~5 steps) MBW Dare & Ties merge included the following models:
NoobAI XL Epsilon-pred 1.1 - Base model for composition
Big Love XL - Base model for photo-realism
Cat Tower (NoobAI XL checkpoint) - Reinforcing composition
Enormous respect to the models creators.
Parameters
For realism: DPM++ (2M, SDE, etc.), Karras, Exponential
For smoother images: Euler A,
CFG: 4 - 7
Prompts
Keep it simple if possible. Excessive quality tags ruin composition adherence. Only put necessary tags in the Negative prompt.
I use:
Positive:
masterpiece, best qualityNegative:
worst quality, bad quality, text, watermark, bad hands, bad eyes, ugly,Description
Reduced realism a little to gain much better prompt adherence in my tests.
FAQ
Comments (10)
madness
lol okay I give up. What the heck is NoobAI? Is it a derivative of pony models? Do I treat it like a pony?
NoobAIXL is a trained SDXL (like pony is a trained SDXL as well) - NoobAI-XL (NAI-XL) - V-Pred-1.0-Version | NoobAI Checkpoint | Civitai.
It is trained on danbooru dataset, therefore knows many artists, styles and characters. Here is the guide to the original model: NOOBAI XL Quick Guide | Civitai.
Many people use to generate images of the characters. I, however, admire its impressive strength to follow complex prompts and create images with complex composition scene (multiple actors). No other models are able to compete to Noob/Illustrious from NSFW complex scene generation perspective.
@wind11 so whats the difference between NoobAI and Illustrious?
@BinaryBottleBake From my uneducated perspective, noob has more characters and composition (e.g. poses, etc.) knowledge and better prompt adherence. Characters knowledge get weaker usually in the realistic merges. I try to preserve the composition awareness.
V02 even better, I love it :)
Yes, I also think v2 is better. Making me very happy!!