For business inquires, commercial licensing, consultation and large scale image captioning for datasets contact me under [email protected], for custom LoRAs visit my ko-fi page.
Checkpoint Type: SDXL, Realism and Realistic
Follow me on Twitter: @YamerOfficial Discord: yamer_ai
If you have enjoyed this checkpoint:
Yamer's Realistic is a model focused on realism and good quality, this model is not photorealistic nor it tries to be one, the main focus of this model is to be able to create realistic enough images, the best use with this checkpoint is with full body images, close-ups, realistic images and beautiful sceneries, for example futuristic cities or insides of a home.
Give this model a chance and let your creativity guide you and the perception you have on the world!
This model is not nsfw focused but it can crate nsfw content, it is preferrable to use a LoRA for specific nsfw content, I also recommended to use words such as: Realistic, Ultra realistic, Photorealistic etc..., to give the resulting image an even better and more accurate realistic look to it.
If you want to explore fields that are not realistic focused I highly suggest to use my LoRA for abstract work and a better ethereal look: Yamer's Style.
No refiner is needed for this model to produce good quality results.
Adetailer is not required to achieve a realistic looking image.
The main style of this model is realistic but that can change with a specific prompt that aims at an anime look for example.饾悤饾悶饾惈饾惉饾悽饾惃饾惂 饾煋 饾惍饾惄饾悵饾悮饾惌饾悶 饾惂饾惃饾惌饾悶
After some time I decided to make some change in the way I release models, the new version will be released in 3 separate models, these 3 models while being similar can still be better with some prompts, that is why it is up to you to decide which is better.
The new version 5 is separated in: TX, SX and RX.
One version can be better with colors or saturation than the other 2; The prompt used in this example is the same, steps, seed and sampler were the same for all images.
Version RX (Realistic + RunDiffusion), SX and TX have been uploaded, enjoy all the current versions of the checkpoint!
Special thanks go to the RunDiffusion team that helped with the release of Realistic 5 + RunDiffusion Photo! Show them some love :3
Version 1, 2 and 3 have the SDXL VAE already baked in, "Version 4 no VAE" does not contain a VAE; Version 4 + VAE comes with the SDXL 1.0 VAE already baked in.
V5 TX, SX and RX come with the VAE already baked in.
Thank you for using my models and writing a review, all forms of support are appreciated, it takes me a lot of time to produce this kind of checkpoint every time! 鉂わ笍
Recommended settings:
Image resolution: 1024x1024 (standard SDXL 1.0 base resolution)
Steps: 30 to 150 (Lower steps may produce image artifacts and other unwanted results)
Restore Face: Not needed to generate high quality images (Not used in the showcase)
Clip skip: 1 and 2 (Works good with both settings)
CFG: 5 to 20
Hires Upscaler: 4x_foolhardy_Remacri or 4xUltraSharp
P探蛽e探蛽r探蛽s探蛽o探蛽n探蛽a探蛽l探蛽 探蛽R探蛽a探蛽t探蛽i探蛽n探蛽g探蛽:探蛽
Quality: 9/10
Realism: 8/10
CFG resistance: 15/30 (going above 15 may result in bad images)
Hires steps: 10-50
Style: 8/10
NSFW: 7/10
1) If you look too closely at the form, you'll miss the essence.
2) Art is not perfect and will never be, it can only improve overtime.
3) I don鈥檛 paint dreams or nightmares, I paint my own reality.
-Tally Hall -Yamer -Frida KahloDescription
This version does not contain a VAE already baked in.
FAQ
Comments (17)
i think you could talk more often with people that knwo what they do... ^^
i dont say that your model is bad !
sry man ! get out of your box or or drink less :D
your pics resolution is in 768 and upscaled, why ?
your prompts are contradict themselves and double ...
some of your prompts are much longer than 150token - that is nonsense !
your negprompt is long as unnecessary and makes your own pictures worse than they are, why ?
The images are 1024x576 upscaled 2,5x because I like the quality, I decided to go with longer prompts because they give the weirdest/most chaotic results, something I really like and I use a long negative prompt because it gives me good results, there is no reason to change that ;-;
I'm sure people will make better art with my model, I just present a basic showcase of what it can do, If you want to share your art and prove why your prompts, negative prompt, image size and other things are overall better for the image output please share your creations!
My bad, you already posted some images :/
Very nice pics, I've decided to feature them on the main page of the site.
@Yamer聽
THY ;)
but why if i copy your image data there written 768pis upscale 2.5x ?
Steps: 150, Size: 432x768, Seed: 3208117246, Model: Yamer's Realistic V4 no vae, Version: 1.5.1, Sampler: Euler a, CFG scale: 15, Model hash: 21642684ba, Hires steps: 25, Hires upscale: 2.5, Hires upscaler: 4x-UltraSharp, Denoising strength: 0.25
@sevenof9247聽that's weird, I never change the image resolution, It is always 576x1024, all the images in this showcase and the other SDXL showcase have that resolution.
It seems you must be confused about what realism means. It means that stuff looks real. The model is clearly not photorealistic as you point out, which also means it lacks realism. So obviously, the focus is not on realism. With realistic in the name, it should make a real effort to be realistic.
Have you even looked at the showcase? Just curious to know.
Oh and btw don't confuse "photorealism" with "realism", those are very different things, this is a realistic model, not photorealistic as said in the model description.
This model is realistic, not photorealistic, it doesn't need to be photorealistic to be realistic, if you have a problem understanding this simple concept please let me know.
@Yamer聽You are just wrong. If it doesn't look real, it is not realistic. If it looks like Pixar, it is not realistic. I don't see a single realistic image in the gallery or in any of the images you post yourself. You might want there to be a distinction between realistic and photorealistic, but there isn't really. The bottom line is it either looks real or it doesn't. In the case of this model, it doesn't. Maybe it's capable of it, but no image has been posted to prove it can.
@AlBat聽0 models under your belt - just shut up and enjoy free stuff, nobody forces you to use it. Also this is my first comment on civitai.
@zz聽thank you for commenting here, and also the support! 鉂わ笍
I always read all comments and respond to good and bad critism ;3
@AlBat聽As pointed out, you are patently incorrect. The difference between realism images (which includes art that isn't obvious anime/cartoon/cell-shaded but rather more-so anime 2.5 and realism illustrations vs. PHOTOrealism is well documented, known and utilized on this site and many others. Seriously, just take 2min and look around before posting what you WISH were the case, but is not. What you are looking for is photorealism, not "realistic" or "realism". The hint is in the word PHOTO...it's not complicated. Glad to help.
@clevnumb聽That's ridiculous. Do you know what the word real means? If something doesn't look real, it does not exhibit "realism" and is not "realistic." The terms are used to try and make people think the model is capable of things it is not. If the model creators were honest, they would give the models accurate names and not make claims that the evidence doesn't back up. It is the people who are misusing the terms realism and realistic who are posting what they "wish" was the case.
@AlBat聽hey, do you know the definition of the term "we do not care", keep your opinions for yourself dude.
Images made with the checkpoint look realistic = name of the model includes the term realistic.
Now, 3 months after your first post, haven't you found any other models to complain on or literally anything else to entertain yourself? Please go and share your negativity somewhere else, your opinions are not welcome here.
Thank you for sharing but really, I can't find who asked your opinion AIbat. Have a good day! 馃樃
If the message isn't clear enough please check this video: https://youtu.be/vAvcxeXtBz0?si=R0onbWh7MMCep4Wx
@Yamer聽Likewise, I didn't ask your useless opinion either. This is the discussion section whose whole purpose is discussing the models. No one makes you read the comments or reply. Go watch some cartoons or something since you love fake looking stuff so much.
@AlBat聽I usually don't respond to replies, but your ignorance infuriated me. Your arrogance in a matter you clearly do not understand. Go educate yourself about art terms and then you can try to correct others, dude. This model description is CORRECT, if you didn't know the differences, this isn't the creator's fault. The one confused about what realism means is clearly you. Why do you think there's a fucking art movement called REALISM? Didn't you go to school?
Here. I can help you a bit: https://www.youtube.com/watch?v=_kXJZAMYYzM
https://en.wikipedia.org/wiki/Realism_(arts)
@Nywl聽Man your own damn link contradict your idiotic comment. "Realism in the arts is generally the attempt to represent subject matter truthfully, without artificiality and avoiding speculative and supernatural elements." Cartoons are not a truthful representation and certainly would be "artificiality."
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.