Update: Please if you see any of my models somewhere else report or let me know! Thnx
Trained with SDXL base model + Flux1D
Can be combined with "Deep Focus model"
Please read about version info.
Feedback and ratings are much appreciated.
16mm (Super) Film Emulator style XL
Anamorphic format film style XL (Hollywood Cinematic style)
Cinematic text title (on screen) style XL
Cinematic "color grading" motion picture film style XL
Cinenaut XL (A TRUE CINEMATIC DIFFUSION)
Cinematic Photography Style XL
Cinematic Kodak Motion Picture "Film Still" Style XL
Cinematic Film Stock Footage Style XL
Cinematic Vintage Film Style XL
High Angle (from above) cinematic style XL
Hyperrealism 3D Cinematic Style XL
Kodak Film Grain (Cinematic) Photography style XL
Infrared Cinematic Photography style XL
Lens Flare Cinematic Reflection style XL
Low Angle (from below) cinematic style XL
Music Video cinematic style XL (Including 60's 70's 80's 90's, etc.)
Point of view (pov + fps) cinematic subjective camera style XL
Rotated View (Dutch Angle) Cinematic Style XL
Realistic Photographic Film Stock Footage Style XL
Set design style (cinematic scenic design) XL
Split Diopter style (Deep Focus) XL
Television advertisement cinematic Film style XL (including fashion models)
Text message on screen bubble (cinematic style) XL
Description
This is an attempt to create a Split Diopter style technique model.
Might not suit everyone needs but still it can produce some cool images.
You can give it a try, additionally you may want to type "shallow depth" etc. in negative prompt. (Might help with results)
FAQ
Comments (3)
Any plans to make a FLUX version? Flux really likes to put the background out of focus
Well, it depends on automatic 11:11 and kohya adding flux support.
@EauDeNoire Protip, use Onetrainer and SDN, both are more up to date and work better, and apart from the PNG info tab, which may be re-added via extensions perhaps, SDN is far more featured. Although if you can handle a little more complexity of setup, with far more versatile and limitless options for workflows, comfy is my primary recommendation for generators. Granted, this message is 3 months old, you may be using diff stuff by now. Just sayin.
I tried to train in kohya, just an sdxl lora with my 4060ti 16gb card, and all it did was throw memory errors, and someone suggested I try onetrainer. it's not immune to memory errors, but it was easier to get functional and actually make a lora with. Also, I just realized you made the flux thing, so anyways.. Sorry, being awake makes me tired.