Update: Please if you see any of my models somewhere else report or let me know! Thnx
Based on sdxl 1.0 model + F1D
Works well with any model. Please take some time and choose which version works best.
Feedback and ratings are much appreciated.
Feel free to check other similar models:
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 more enhanced version of the model. (Trained on many 3D hyperrealistic images)
You can mix it with any other lora model(s) you like. (You need to play with weight to get best optimum results)
FAQ
Comments (10)
Still wonder how you do it. I mean...some time ago you popped out of nowhere on civitai with so many lora's that are actually really good. Some even fantastic and have become my favorites. But how you do it I have no idea.
It's normal image training on large dataset. (The base model plays an important part in process)
@vantablackdark Hi there, did you use the base sdxl model for the training ? Thanks
@Zojix yes, it's written in description. You can also check "about this version" for more info.
@vantablackdark ah yes sorry! Quick question, is regularization images useless for train a checkpoint ? Thanks!
@Zojix Honestly, I have no clue. I haven't tried training a checkpoint yet. Very hard to train one. Lora's are much easier. Less hassles.
But in general, when training lora's, I haven't used regularization images.
My personal opinion, they aren't that important if you use many images. (My personal opinion)
I think, they might work better, with small batch of training files.
i know this is an old question, but the answer is because this creator @EauDeNoire
works pretty good on humans, but gets a little blurry on "amazonian" forests, rainforests and so for me. Anyone else experience that?
Try playing with lora weight, might help a lot. Also, try using different base model(s) till you find the best model that suit your needs. Also, try using words like "clean sharp epic image of" etc. in prompt. And use words in negative prompt like, "blurry, out of focus, bad image, etc.
@vantablackdark thanks, this community is the best!