TL;DR; tiny FP8 model with quality of FP32; merges allowed (please mention this model); improved single pass eyes and fingers correctness; optimized combination of sharpness and realism of CinEro Illustrious V2 with cinematic style and creativity; precise details and cinematic look; light particles.
Note: Tested in A1111 and ComfyUI. For A1111 I recommend to turn off the "--xformers" as it didn't work with latest PyTorch.
Hey guys and gals!
No EA AGAIN 👇
Thank you SO MUCH for support on V2 and V3. I've nearly 10k of BUZZ on training with new datasets. Some of expanses were compensated by the donation from kind supporters (MANY THANKS AGAIN!!). Some of expenses wasn't recovered.
This is why I need to shyly encourage you to post images (bad and good are welcome), tell your friends about my creations, leave a feedback. That's the only thing fueling my progress.
Just 150+ postings will compensate training costs at CivitAI. You can also collect this model or interact with my images. This is just a TIME for you but IS A GOLD to me.
I don't ask you to donate YELLOW BUZZ, but will be very glad if you spare some. No matter what, all my BUZZ will be spent inside CivitAI on training new models.
[DISCLOSURE] I am using the Post-Maker (3-pass workflow) to produce HQ images using only the released model. You can download it and modify the Steps or resolutions. Steps 30 for 1st pass and 8-10 steps for 2nd and 3rd passes are enough to produce good results 90% of tries. 3rd pass is not so important.
Description
FP8 UNet + FP8 TE (3.5Gb).
XYZ Plot used to compare it with internal FP32 model. Difference is minimal.
FAQ
Comments (2)
THE SIZE... 3.5Gb for the quality of 6.5 FP16. That is lovely SSD space saver.
In A1111 there was an issue of compatibility on my side. But I removed all outdated packages (deleted venv) and re-installed the latest. As suggested I turned off the xformers (new PyTorch is fast enough without it). So, now I have a good realistic SDXL model with twice lower size on SSD.
In ComfyUI it works smoothly and fast. It sometimes renders a strange circular pictures with the given ComfyUI workflow (suspecting the embeddings effect). But it gives a very sharp picture even in single pass. Eyes are almost perfect (second pass makes them ideal). Fingers almost good (rare 6th finger occasionally). It is super creative and realistic same time.
THANK YOU SO MUCH! I love it. No yellow BUZZ but I will try to give you a blue BUZZ!
Thanks for feedback and support! I Love It!