Welcome to epiCPhotoGasm
This Model is highly tuned for Photorealism with the tiniest amount of exessive prompting needed to shine.
All Showcase images are generated without Negatives (V1) to show what is possible on the bare prompt.
Whats special?
The model has highly knowledge of what a photo is, so if u promt u can avoid using photo. If the prompt tends to be fantasy like the model will turn away from photo and u have to tweak by prompting and/or negatives.
The model can do various ethnicities well, so try them out.
Age is also well trained and known by the model, so try them out too.
How to use
use simple prompts without "fake" enhancers like "masterpiece, photorealistic, 4k, 8k, super realistic, realism" etc.
don't use a ton of negative embeddings, focus on few tokens or single embeddings
you can still use atmospheric enhances like "cinematic, dark, moody light" etc.
start sampling at 20 Steps
no extra noise-offset needed
Additional Ressources
Style Negatives: colorful Photo | soft Photo
Useful Extensions
!After Detailer | ControlNet | Agent Scheduler | Ultimate SD Upscale
⭐ Feel free to leave Reviews and Samples - and always have fun creating ❤
Description
Okay okay, can we even get more realism? Whats Different? I added a trained Lora which was meant to be a Dodge and Burn Filter, turns out it boosts reality pretty much, so i merged it into my model 😘 Let's see what you guys say.
FAQ
Comments (17)
Tested v2.... in comparison I like the first version much more. Stick with with v1!
same hahaha
I disagree!
I humbly disagree as well. This model understands the prompt better and does ethnicity much better too.
@itsnotreubs Its my personal opinion and its good to have 2 versions! Everybody can be happy :-)
@CyclopsGER now we have 4 🤭
@epinikion I will try it out tomorrow :-)
3.1 so far is creating very good results. v1 is still my favorite but this is also good :-)
Great job!
I found 3.1 to be a huge improvement over the previous epiCPhotoGasm models. It does a much better a job at following my prompts (as the name implies, hah!) while still keeping the greatly increased image fidelity it has over other modes intact. I think it came out great!
Update.... after creatinng 1000s of images. 3.1 is really fantastic! Currently my favorite checkpoint!
@CyclopsGER Good to hear. Thank you for using it ❤️
nice work!
would you tell me how you train this model?
So which is better? This or epiCRealism?
Yes :) ... just Yes.
(because "better" is subjective)
I am using both but find this a little better.
I have been testing both for some time now, epicrealism is great for closeups, this model is good for full body portraits. Atleast with my settings.
why compare those, seems so random..
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.