THRILLustrious

By pAInCREAT0R

"LIKES" are appreciated as it is the only way creators not in CIVITAI's creator program get their work noticed. - Thanks!

Putting the THRILL and more 'real' into Illustrious

THRILLustrious is my attempt to take the Illustrious base and train it to a more realistic aesthetic. The challenge is to continuously add realism aspects without sacrificing the base flexibility and concepts of the base model. This is a bit more difficult with Illustrious because many of the concepts baked into the base model are artistic/anime at their core. So it is a constant battle of training up the realism, then merging the concepts back, repeat... For that reason, you may notice that the BETA release looked slightly more realistic - but at a greater sacrifice of concepts.

For V1 Genesis, I started a completely fresh training on the base of Illustrious XL. I then merged that new checkpoint with BETA and trained on the resulting Checkpoint. The idea was to continually reinforce the concepts in the base model while pushing the aesthetic toward realism. This approach diluted the residual impact of the models merged into BETA.

This is still a work in progress. You will not get the level of realism that you can from my PONY or SDXL models. I do think it is a solid enough base checkpoint now thought to officially call V1. As time allows, I will refine and update it if possible.

I am not great at prompting Illustrious models yet. I spend more time in FLUX and PONY. But I thought the early results were worth sharing. Hope you enjoy. If you want this one to keep being trained, give it a like or leave a comment. Better yet - post some images you made with it in the gallery!!! (I don't need your buzz!!)

I have been using Euler A, SGMUniform, 40 steps, 2-5CFG. However, I have not experimented with it enough to say that is optimal. The model benefits from HiresFix pass. You may occasionally need to use Adetailer on eyes or teeth.

How BETA was made:

All training was done in Kohya starting with the Illustrious base model. No text encoder training at all - only UNET. With the recent Kohya updates, you can do higher batch and gradient sizes at faster speeds than ever. So on my 4090 I could batch 5 or 6, gradient 5 or 6 to get a virtual batch size of 25-36. This made it much faster to train than in the past. (Honestly, this was the only reason I attempted it after finishing PONY model.) There was some DareMerge of a small amount of my FULLY_REAL_EXTREME model and Redcraft Illustrious model to smooth out aesthetics and add a little more flare. About half the training was done at 1024 and half at 512. It could use another pass at higher resolution to help the faces. I preserved the clip from Illustrious 100% though and did not train encoders at all. (I figured I would mess it up.)

Disclaimer: This model is provided for educational purposes and for the advancement of AI art in general. The creator of this checkpoint assumes no responsibility or liability for the end user's outputs. Any illegal, unethical, or deep fake use of this model is the sole responsibility of the user engaged in those activities. The end user assumes all liabilities from use of the checkpoint.

No permissions are given for anyone to distribute this model on other sites. I do not give permission for it to be used on any image generation service other than CIVITAI.