ModelsLab/CinEro XL | Photomatic Cinegraphy - Moody Creative Cinematic - 👎 V1.4 RC5 Bokelicious

BOKEH! DO U ❤️ IT?

If you do ❤️ it as I do... test this version in some creative manner and give me feedback.

This will motivate me to continue to improve the quality of Cinematic Photography models.

FOCUS: 💥 HIGHER CFG RANGE 💥 (tested with vals of 4.3...11.3); 🟢 correct hands, 🟢 fingers and anatomy; 🟢 lovely bokeh renders and cinematic grading; 🎨 creativity (artful fantastic detail).

This version should render shallow depth of field and bokeh by default (no need to use these words in prompt).

Try to use "f4.0", "f8.0", "f11.0" aperture triggers to reduce bokeh effect if you don't like it. In some cases it can help.

Also, I tested this version with and without triggers like "ideal feminine hands", "correct fingers", "perfect hands" with different success rate. So far I can't tell that these triggers are important for correct anatomy.
Will be glad if you test this version on anatomy correctness (SoftCore).

HardCore NSFW was out of scope of the training ;)

PS: can't tell you the precise numbers because there was few sessions of training with different datasets, batch sizes and gradient accumulation steps; so it nearly impossible to come up with equivalent numbers of batch size 1 and gradient accumulation 1. Sorry...