This model represents the original Willy’s Noob Realism line and is now considered the Legacy branch, while ongoing development has moved to Willy's Realism.
This model and its version(s) were merged for the sole purpose of finally having a decent out of the box consistent Realism model based on Noob. The "HD" and "V-Pred" versions are made for higher resolution raw gens and upscaling.
!!! If you are having problems, noisy images, or prompt issues please scroll down to "Common Problems" !!!
Version Information
V-Pred v2.0
This is the second version of Willy's Noob Realism V-Pred.
This version is almost a hybrid between the old style of model and the newer V-Pred v1.0, allowing for both darker scenes, and bright natural lighting scenes similar to that of the old EPS models and the V-Pred alpha.
As I slowly continue to try to improve on my models, I've found it getting harder and harder to improve the quality of the model without causing significant other issues or significant notable loss of knowledge in certain areas.
In this version I've replaced the clip-L and tweaked the models using my own and other specific loras.
This version works well with CFG 4-9. The lower the CFG the more balanced the colors, working better with darker scenes, and higher CFG works better with saturated colors and bright scenes.
V-Pred v1.0
This is the first release version of Willy’s Noob Realism V-Pred.
This version is a bit different from the earlier versions of Willy's Noob Realism, so you can expect it to behave differently in some ways. While there’s a bit of style loss compared to before, this version keeps the high resolution detail and realism—and, most importantly, it reintroduces proper lighting overall, which every previous version struggled with.
Getting this V-Pred model where I want it has been way tougher than I expected. What I thought would be a quick process turned into weeks of experimenting just to find a way to bring proper lighting back into a model that seemed almost incapable of handling it. (For perspective, getting from v4 to V-Pred alpha only took a single day—everything after that has been the real grind.)
What I’ve learned along the way is that both the style and the lighting issues both sit in the same weight layers. That makes fixing them tricky, since the options are either doing some pretty janky merging, or spending a ton of time diving deeper into each layer and many hours of experimentation.
This version works well with a CFG of 5-7. Lower CFG is better for darker scenes while higher CFG is better for brighter scenes and more saturated colors.
V-Pred Alpha
V-Pred Alpha is the first version of Willy's Noob Realism that uses v-pred instead of eps noise prediction.
This version is capable of more vibrant colors, and overall darker, and lighter images.
Being the Alpha version, its far from perfect. Fixing the "spotlight" issue from eps, and training back in proper dark lighting for dark scenes was taking significantly longer than I anticipated, so I decided to release the initial version now rather than making people wait longer while I continue to play around with datasets and training settings.
V-Pred models don't typically play nice with play nice with a lot of sampler & scheduler combinations. So with this version you might have to play around to find what works right, or you can go back to v1.0's recommended sampling settings which work perfectly fine.
HD v4.0
HD v4.0 is the newest and final version of the "HD" series of Willy's Noob Realism models. This version was made as a final attempt to increase realism, while reinforcing previously lost knowledge and further stabilizing the model.
This version can generate realism without the usual required quality and style tags, and does not need any negative prompts.
Where do we go from here?: My next goal is to make a proper v-prediction version of Willy's Noob Realism.
HD v3.0
This version was merged to further increase realism, allowing for more variety and expressiveness. Fixed foliage and most backgrounds while limiting excess noise.
This version has been tested with both Euler A & Beta, and DPM++ 2m SDE & Karras and works with both tag based prompting, and some natural language prompting.
(Works best with just tags, or a combination of tags and natural language)
HD v3.0 has improved stability at higher resolutions, capable of fully stable 1920x1920 raw generations, and 2048x2048 raw generations with minimal to moderate issues depending on prompt and aspect ratio. Raising the CFG can increase stability further with problematic prompts at 2048x2048. (Skimmed CFG can be used to decrease oversaturation caused by high CFG)
HD v2.0
This version was merged to increase realism, while attempting to fix the problems with noisy backgrounds, while retaining its knowledge of complex topics and species. Can generate raw images up to 1920x1920 with minimal issues.
Uses the same version specific settings as HD v1.
HD v1.0
This version was made to increase realism, while allowing for higher resolution base gens with the quality of an upscaled image! This version is capable of generating images from 768x768 to 1920x1920 resolutions without breaking.
Version Specific Settings:
Prompting is the same as the other models, but to get the most detail out of higher resolution images generating images with at least 50 steps is suggested. Please refer to the "Recommended Settings" for more information.
If you are getting images with unintended multiple characters, make sure to include the tag "solo".
Longer, more detailed prompts result in more stable and typically more detailed images.
Certain prompts may not be fully stable in this version, so play around.
v2.0
This version uses the same settings as v1.0, and is an overall improvement in realism, and better support for upscaling.
v1.0
Initial release version.
Recommended Settings:
TL:DR Its very simple, just prompt however you usually would for noob, but add "realistic", and "photorealism" after your quality tags.
I suggest using Euler A with Beta scheduler, or DPM++ 2m SDE with Karras scheduler (does not work with v-pred) at a CFG of 5-7 and steps of 20-50, but feel free to experiment. Not all schedulers and settings work for everyone.
Here's a positive prompt example:
<quality tags>, realistic, photorealistic, <style tags>, <character tags>, <pose tags>, <background tags> And here's a basic filled in example:
masterpiece, best quality, highres, absurdres, (realistic, photorealistic), 1girl, solo, anthro, wolf, grey fur, posing, bedroomAnd here is my suggested negative prompt:
(Negative prompt is no longer needed for quality images)
worst quality, low quality, normal quality, monochrome, bad anatomy, ugly, (illustration, cartoon, anime), flat color, outline, smooth skin, blurry,These are my personal recommendations, but feel free to experiment and use what ever settings you feel works for you!
Common Problems:
My recommended settings aren't set in stone, just my own personal preferences from testing and using the model in ComfyUI
Unless you specify a gender, it will automatically generate female characters or characters with breasts due to its bias towards women.
The tag "1girl" can cause issues with certain prompts when trying to generate realistic humans. If you are getting strange outputs, try just using the tag "female" instead.
If you are getting unwanted multiple characters, make sure to include the tag "solo"
Beta scheduler is not properly implemented in Forge and will result in heavily artifacted noisy images.
Here is a list of working Schedulers for Forge: https://civarchive.com/posts/11756794
From my testing Beta scheduler does work in Reforge however some have been experiencing problems. I suggest you make sure Reforge is up to date before complaining to me. Otherwise most other samplers work perfectly fine in Reforge.
Here is a list of working Schedulers for Reforge: https://civarchive.com/posts/11756585
Nobody using A1111 has actually expressed any issues. If you are having issues with A1111, I would suggest verifying your settings.
Here is a list of working Schedulers for A1111: https://civarchive.com/posts/11757173
Some people have also been experiencing small VAE artifacts while using Reforge. This is likely due to your VAE settings not being set correctly. This model uses the default sdxl.vae.safetensors sdxl VAE.
Some EPS loras can cause problems with the V-PRED versions of this model such as the EPS "spotlight" effect, making night/dark lighting brighter, or colors less saturated.
Other information:
This model was merged with furries in mind, but is fully capable of generating all kinds of realistic humans and humanoid fantasy species. I have extensively tested it with all kinds of different unique furry species, all kinds of humanoid fantasy creatures, and humans. I have also tested its compatibility with SDXL, PDXL, IL, Noob loras. Most loras trained on proper tags will work with the model, although Noob loras work best (since that is the base model for this merge), and other SDXL based model loras will likely work with varying success.
"Fake slider" Pony loras will not work, as those are trained on Pony's quality tags for activation (There are very few of these, so just be warned).
I plan on making better versions of this over time as more resources come out, or if I have time to make some realism or other Loras to further fortify it.
If you have any issues, feedback, or suggestions feel free to let me know in the comments!
Description
FAQ
Comments (14)
I've never commented on a model before, but I must say: you COOKED for this model.
I've never been able to 1 shot gen anything at 1920x1920 before. Seriously amazing for realism/3D. Thanks for sharing!
Thanks.
I already have a better version in development :3
@willywizard Stoked!
The overall results of both HD Ver 1 and 2 are incredible and outstanding! I am noticing, however, that all of them are pretty high-key as far as overall tonality. They all look as if they are sitting in direct intense sunlight, very pale with a bright beige and pastel blue color palette. Any suggestions on how to get darker colors in the rendering?
You can modify your prompt to try to include things to do with sky/time/brightness/lighting/shadows/ect. Unfortunately though EPS models do things in a specific way, if you average out the colors of any EPS model's image, you always ends up an almost neutral grey due to how it evens out the noise when denoising, and I hate it ngl. I much prefer v-Pred, but theres not a lot of content for sdxl v-pred models for realism, and merging EPS into v-Pred although not impossible is such a pain. Typically theres gonna be some blaring brightness in the image, or its going to be of fairly uniform brightness.
Best ways to deal with it in any EPS model is to include descriptors to do with background, lighting, time of day, ect. There are Loras out there that can help, but their effects are hit or miss. You can add specific tags like "Black background" can help, but try to never use "dimly lit" because that basically tells the model "Hey! I want the whole image to be of uniform brightness" which can cause problems. The other option is img2img with a purely black square at fairly high denoise. or just straight up using "Krita diffusion" for on the fly img2img and inpainting with a comfy back end, I personally use it for images that I am having a hard time getting just right.
1. Will there be a model for Illustrious for more compatibility? It's much more popular and works better.
2. I also have terrible focus on forge. I made the settings recommended by the author, but they don't help at all.(tried everything I can and always the focus is lost). Is there a way out? This is a problem with all checkpoints.
By the way, in the author's picture of the girl sitting in the chair the focus is just as lost on her legs.
1. This is Noob based which is itself based on Illustrious. It should have no compatibility issues with any Illustrious, or Noob resources. It should also work any specific tag based prompting style given you use the required quality tags for the model and any additional activation tags you might need for any Loras you try to use. All noob is, is illustrious with additional training. (It is also moderately compatible with SDXL and Pony resources)
2. In common problems I mentioned that Forge does not have properly implemented schedulers and will not work with my exact recommended settings. I personally suggest using reForge, a1111, or the one I personally use ComfyUI.
In the image of the girl sitting on her chair, her legs are not of the main focus of the image and any blurriness is either due to the way It was prompted, or pure RNG and had nothing to do with any issues with my own generational settings. I do however understand why you compared them.
You should be able to fix your issues if you use the recommended settings in any other UI, or if you play around with different schedulers in forge. If I remember correctly simple was a good alternative to beta in forge.
@willywizard Thanks for the reply. I will try to switch to reforge.
I also have lycoris not working in it.(The lycoris extension does not allow you to browse loras.)
@willywizard I tested in reforge and abandoned it immediately after the test(it is outdated and unsupported). Also tested in cpnfyui. In both results the picture was more contrasty. But fuzzy image was every once in a while. I also took your picture as a basis and inserted it in confyUI and with another sid sometimes the focus was lost. Maybe it's the furry models, now I'm trying Nova Animal XL and it seems to me that all furry-realism has it. Thanks for your help:)
@alexplay52 reForge was only abandoned around a month a bit a bit ago, half of its features are still better implemented than Forge from what i've seen, either way its up to you what you use, i only offered my suggestions. I've never played with Nova Animal XL so idk how it works. Good luck.
If its a dedicated furry model i didnt say anything, just saw a human girl on main pic:)
@donaldsolberg962 it was made with furries as the main focus, but it is fully capable of generating realistic humans. However humans will typically look very generic or similar unless you go into detail in the prompt about the humans appearance. The model understands some (but not all) races as tags, and even can understand some natural language if tag prompting is not enough to get what you want.
The longer and more in-depth the prompt, the more natural the humans will look. Although certain tags will still have slight or possibly major style bias that can cause style deviation.
Great model. Would love to see a v-pred version cause v-pred's realism is lacking.
I was working on a v-Pred version, but merging EPS models into v-Pred is a pain in the ass and takes a while. Ill give it another go, but because as you said there isn't much for v-Pred realism its difficult to just swap it over without causing significant issues.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.