You can also run this model on Magespace and Sinkin.ai!
https://www.mage.space/ (Really helps out if you want to support to)
Want to send some support? (Buy a cup at Ko-fi)
A branch off CheckPoint from RealCartoon3D
The Process:
This Checkpoint is a branch off from the RealCartoon3D checkpoint. This one's goal is to produce a more "realistic" look in the backgrounds and people. I am trying to avoid the more anime, cartoon, and "perfect" look in this model. It is a challenge that is for sure; but it gave a direction that RealCartoon3D was not really moving toward (as I wanted that one to just do what it is asked with a nice fun look). The process is the same as the base checkpoint (RealCartoon3D); but I look for more "real" merges. This (like the others) gets updates from RealCartoon3D as well. As with the base model, I try not to use checkpoints that are restricted on merges.
The Settings:
Width: 512 (normally would not adjust unless I flipped the height and width)
Height: 768 (Have done up to 1024, but 904 is doing really well)
Sampling Method: "Eular A" became pretty much the default as versions moved along, but "DPM++ SDE Karra" and "DPM++ 2M Karras" are favorites for me as well.
Sampling steps: 30-50 normally (30 being my starting point, but going up to 45 a lot of the time)
Hires.fix settings: Upscaler (R-ESRGAN 4x+, 4k-UltraSharp most of the time), Hires Steps (10-20), Denoising Str (0.34 - 0.45 normally), Upscale (1.5 or 2 does well)
Clip Skip: 2
Would run ADetailer to help enhance the eyes but many times in the later versions I would not run this as it was not needed.
Why So Many Versions:
Because I wanted to share all the results that I felt reached a desired outcome. Allowed me to have fun, and I saw that many enjoyed them. Which motivated me to keep trying. Again, thank you.
__________________________________________________________________________________________________
License & Use
This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage.
1. You can't use the model to deliberately produce nor share illegal or harmful outputs or content.
2. The authors claims no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in the license.
3. You may re-distribute the weights. If you do, please be aware you have to include the same use restrictions as the ones in the license and share a copy of the modified CreativeML OpenRAIL-M to all your users (please read the license entirely and carefully).
Please read the full license here Stable Diffusion
Use Restrictions:
You agree not to use the Model or Derivatives of the Model:
- In any way that violates any applicable national, federal, state, local or international law or regulation
- For the purpose of exploiting, harming or attempting to exploit or harm minors in any way
- To generate or disseminate verifiably false information and/or content with the purpose of harming others
- To generate or disseminate personal identifiable information that can be used to harm an individual
- To defame, disparage or otherwise harass others
- For fully automated decision making that adversely impacts an individual’s legal rights or otherwise creates or modifies a binding, enforceable obligation
- For any use intended to or which has the effect of discriminating against or harming individuals or groups based on online or offline social behavior or known or predicted personal or personality characteristics
- To exploit any of the vulnerabilities of a specific group of persons based on their age, social, physical or mental characteristics, in order to materially distort the behavior of a person pertaining to that group in a manner that causes or is likely to cause that person or another person physical or psychological harm
- For any use intended to or which has the effect of discriminating against individuals or groups based on legally protected characteristics or categories
- To provide medical advice and medical results interpretation
- To generate or disseminate information for the purpose to be used for administration of justice, law enforcement, immigration or asylum processes, such as predicting an individual will commit fraud/crime commitment (e.g. by text profiling, drawing causal relationships between assertions made in documents, indiscriminate and arbitrarily-targeted use).
Terms of use:
- You are solely responsible for any legal liability resulting from unethical use of this model(s)
- If you use any of these models for merging, please state what steps you took to do so and clearly indicate where modifications have been made.
Note:
If you see any conflicts or corrections to be made, please let me know.
Description
Just continuing the adventure of trying to get this RealCartoon-Realistic checkpoint to do well in realism with a mix of things that are not...but the checkpoint tries to make it seem like it could be real :) Overall, I have enjoyed the responses to the prompts. I hope you all enjoy!
FAQ
Comments (19)
Interestingly, I have v12 in my photo category, while 11 and 13 ended up in render models. I think this model is probably very close to realism.
Many of my models have only been tested briefly to ensure quality and categorize them, but I'm going to have to look at these more closely and try a few things to see what they can really do. It's probably a couple loras away from doing a nice photo quality with the creativity of a render model, which only the Ani-models have achieved so far, in my testing anyway.
Looking forward to your findings :)
Hello. Why do Seaart have two versions of 14? Which one should I use?
I must admit, I am unsure why. One should have the normal covers I apply. That is the one.
They're just both on your account. That's why I asked. As far as I understand, there is no difference between them.
@barinovrs433 Think that is a bug...I went and checked and it looks like they are synced....which is weird. Sooo, they should be the same :)
Am I the only one thinking v11 is 1000 times better than v14 ? 🤨
It is one of the more popular ones that is for sure. I think V14 though has a nice style that tries to maintain realism with non-realism. I like that fact people are enjoying lower number versions :) Along with the later ones.
@7whitefire7 Yep ... no matter what ... thank you for sharing your hard GOOD work 👍💕
I wish this were available for onsite generation like your others, really cartoon is one of my go too's
I am unsure why...will have to ask
@7whitefire7 I've come across this with a couple of creators, I think civitai may be constipated
This Model Absolutely Nails Prompts and LoRa! Seriously awesome job on this my friend. I'm going to be downloading your other models for sure!
Sry for this noob question, i started looking at ai generation image onlly few day ago, and i'm still confuse about some thing but mainly i would like to know about pruned vs unpruned version, i learn that pruned is lighter version in term of space mainly that what i remember, but does it also come with bad side ? like not so great quality or idk, if we don't have trouble with space should i go for pruned still or unpruned version ?
By the way your model look realy great,i'm gonna try it soon enough as i setup all thing.
When it comes to image generation there is pretty much no difference. The larger is better for those that want to merge checkpoints.
@7whitefire7 thx for the quick reply
hi i tried to upload an image i made using your model, but do you know maybe why she appear so small on the preview in the gallery ?( the one with the angel, or just check my name) is it because she is a 16/9 ? instead of a portrait like the other ? because she is quite big in reality she is over 4k resolution size so not sure why the preview is this smalll...
It is how the site thumbnails landscape style images. Kind of a bummer :/
@7whitefire7 yea really :/ thx anyways for the comfirmation
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.






