This is my next LoCon that I trained thanks to this guide:
[Guide] Make your own Loras, easy and free | Stable Diffusion Other | Civitai
Argie Film - Portrait (Check 2.1 version to see details about how to use it, here is for 1.5)
Inspired and based from Argentina Film Photography Aesthetic and Style.
There are LoRas and Checkpoints that reference the Analog / Film style like RZ - Analog, which I admire and took inspiration from it.
So I recompiled a lot of film pictures from my own to trained. It was intended for portraits more than for full body, for landscapes and others, I am not 100% sure that it works well.
It was trained by approximately 1200 portrait-type photos extracted from my personal film pictures that I took in the past with a film camera.
In the training I used this checkpoint with SD 1.5 as a base, so I also recommend that you use this checkpoint in conjunction with the LoCon to obtain the most faithful result to the one I had.
Also I experiment in its use with this checkpoint. (Use its own prompts + prompt I recommend below)
(Surely there will be better combinations, better options, but that I have not tested or documented.)
How to install LoCon:
How to use it (There is no a trigger word):
Prompts: analog style, film, dust, grain, (film grain:1), photography of a + yourprompt, detailed face,
I also recommend using epiNoiseoffset_v1.
Sample: analog style, film, dust, grain, (film grain:1), photography of a 20 years old Golden blond hair Belarusian woman at the beach, detailed face,
Negative Prompts: rz-neg-foranalogportrait (download here)
You can experiment with negative prompts, but for me ‘rz-neg-foranalogportrait’ give very good results.
I recommend these parameters:
LoCon Strength: 1.0
Size: 512 x 512 - Truly I have not tried with other resolutions, I think the most stable is this measure.
CFG: 9.5 is perfect (in my opinion)
Sampling Steps: between 20 and 40 is the most stable. (40 more details)
Sampling Method: DPM++ SDE Karras works very well for portraits.
I used this LoCon in img2img and its not gives very well results. (But you can try)
I invite you to experiment with checkpoints, mix them with other Loras and share them!
Don’t forget to put the prompts you used, thank you!