Type | |
Stats | 5,040 5,998 |
Reviews | (432) |
Published | Aug 23, 2024 |
Base Model | |
Training | Steps: 3,185 Epochs: 14 |
Usage Tips | Clip Skip: 1 |
Hash | AutoV2 5F3486225F |
Recommended Settings:
DPM++2M - SGM Uniform
2.7 Distilled CFG
LoRA Weight 0.5 - 1
20 - 30 Steps
Feel free to test other settings and comment on them.
---------------------------------------------------------------
We have several models that make images more realistic, so why am I launching this one?
Unlike the other models, my goal is to bring more realistic textures and lighting, rather than a boring conventional photograph.
The effect sought is as if it were taken with a professional camera, but without that painted look that the base Flux brings, even when using terms in the prompt to achieve realism.I uploaded a collection of images comparing the same prompt and seed, with LoRA (right) and without LoRA (left).
Notice the texture and light details that the model brings to the image.
And this isn't limited to real photography and people; it can be applied to creatures, landscapes, animals, abstract art, and whatever your creativity allows. It works very well when combined with other LoRAs.
I am very curious to see the possibilities of this model, so please share as many images as you can here and give me feedback so I can further improve the model.