Want to send some support? (Buy a cup at Ko-fi)
This model's earlier Versions (1 and 2) were created with parts of Aniverse! Samael1976 has authorized it, so please go support him as well!!!
So Why Another Checkpoint:
Many have wanted a bit more 2.5dish. So, I wanted to see about getting that to you all. This checkpoint will try to maintain that 2D look with a splash of 3D in there. Of course some prompts may pull out a more 3D look; while others may go full 2D....but hopefully that does not happen to often. LoRas will of course affect the look as well; but either way...I hope you all enjoy!!!
Starting with RealCartoon3D V11(was working on a 12 at the time) I was trying to get a more 2Dish look going. I was doing this because many wanted something that was more 2.5D (The checkpoints used for merging do/did not have restrictions on checkpoint mergers or are able to have different permission when sharing merges). I also baked in the VAE (vae-ft-mse-840000-ema-pruned). I tried ClearVAE, but it would mess up from time to time (which may have been my computer). I did not want this issue to fall to anyone that downloaded this model, so I did not use that VAE. In the process of the merges, it looks like one of the models used contained Aniverse information. This was not intentional; but as you can see the results are pretty nice. Samael1976 and I talked and decided to allow it to move forward as more of a collaboration. I hope you all enjoy!! Maybe someday we (Samael1976) and I will do a full merge of them and share. :)
(These settings are for A1111 ):
The below image is the top settings I recommend. I do not use a VAE normally as
(vae-ft-mse-840000-ema-pruned) is baked in.
Below are the normal settings I do run when generating most of my images.
Some variation of course happens depending on the desired outcome (I.E. Landscape). I also like to make portrait 512 by 904 as well. I only run batches when I am checking checkpoints or looking for that perfect image. This is normally set to 1
Sampling methods DPM++ SDE Karra and DPM++ 2M Karras do well as well.
Upscaler is either R-ESRGAN 4x+ or 4k-UltraSharp for most of my images.
The Upscale settings will vary depending on your computer.
Would run ADetailer if subject is in the distance as SD1.5 can sometimes fail at faces with distance people. Be careful if you have blurred subjects in backgrounds; as this can start "enhancing them" and thus mess with the overall look.
If you are having problems running A1111 you can change the "webui-user.bat" settings to help (by right clicking and opening in notepad):
set COMMANDLINE_ARGS= --xformers
If you do not have xformers or cannot install it, put the following instead:
set COMMANDLINE_ARGS= --disable-model-loading-ram-optimization --opt-sdp-no-mem-attention
To install xformers: how to install xformers
When it comes to prompts that is really up to you. Here is some advice:
Please be careful on the strength you add to LoRas as this can affect the overall look with the checkpoint. Stronger does not always mean better. I normally run 0.4 - 1 strengths depending on the LoRa.
What is first in your prompt has higher priority.
Having parathesis increases a priority, but having everything in them is almost as good as typing without them.
Subtle changes in a prompt (to include punctuation) can change the image
The seed helps in producing similar images with similar software and settings. It does not guarantee the same image as even a difference in software (I.E. ComfyUI) or hardware can affect it.
If you want a more cartoon look (at least with this checkpoint) use the following near the front of the prompt: Anime, Cartoon, painted, or comic. This does not guarantee a look depending on the version; but it will lean more that way. This also works for Realistic looks (Realistic, real, etc).
If you want Safe for work or not nudity to show up then make sure you put the following in your negative prompt: nude, nudity, naked, NSFW, nipples. Of course if you have this in your actual prompt then it will more then likely do it.
The following is what I normally run in a negative prompt (you can click on easynagative or badhandv4 to get the files):
NOTE: Badhandv4 is an embedding. So goes in the embedding folder of A1111
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
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).
- 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.
If you see any conflicts or corrections to be made, please let me know.