[Leeloo Please JPG]
DO ME A FAVOR if you like what I'm doing...
Please consider to test my trained models with different topics and compare it with another models in order to see if my goodies are adding anything of value to the SD world. I will be glad to get a constructive feedback about what is GOOD and what is BAD about my models.
So, by adding the REVIEW with comments you will help me to get energy and motivation to move on.
Thanks in Advance!!!
!!!NotaBene!!! Load my example images to ComfyUI.
I use complex and simplistic ComfyUI workflows with upscaling and without. To get a tips for prompts you can press a "NN Nodes" button in image resources and paste it to ComfyUI.
Also, I often repeat some popular prompts from version to version in order to show the difference, so you can compare and get an idea of what's new.
MAIN GOAL
Main focus is a balance between photorealism, creativity, bokehlicious rendering with shallow depth of field, anatomy improvements, emotions, artistic and analog style.
PS: if you like what I'm doing you can Buy me a Coffee
Description
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...