Follow me on Patreon!
SoReal! - Vintage Photography
Compatibility & Usage
Due to it's small size and rank, the model should have a minimal influence on the base model, further improving compatibility with other LORAs across Base/Turbo and indeed other checkpoints.
'Trigger words' aren't real - don't ask for one, just prompt normally! 'Vintage Photography' appeared often in the captions.
Future
Future iterations of this model will see stronger prompt adherence, anatomy adherence and general composition and quality through +/- reinforcement learning.
I am planning on finetuning Z-Image considerably with a model called 'SoReal!' (Or, alternatively, ZoReal!). However, I want it to be the best possible amateur finetune possible, to achieve this, I have:
1. Trained a custom quality model.
2. Trained a custom one-shot demographic model (height, weight, skin tone, ethnicity, age in years, body shape) with an average accuracy of 89% for top-confidence prediction using ConvNext-XL.
3. Finetuned wd-tagger-large-v3 on a large sample dataset of 50k hand-tagged images with human-assisted active learning.
4. Fed those tagged images (with quality, demographics and general labels) with the image metadata (incl. EXIF & Camera Metadata) to Gemini 3 Flash for generating captions.
No over-trained LORAs baked in, no dramatic loss of generalisation, just a good, all-round, NSFW-ready, finetuned model.
I am now severely limited, however, by my compute and financial situation, so if you'd like to help make SoReal!, well, so real, then you can follow me on Patreon!
Licensing
If you'd like to release a merge of this model, please contact me.
Made with <3 By BitcrushedHeart