Combining my two favourite models, KasyElements emerges as a mix of painting and semi-realism. At its heart lies the EtherBluMix5, contributing to 70% of its essence with its distinct flair for vibrant colors, expressive backgrounds, and a painterly atmosphere. But what sets KasyElements apart is the 30% infusion from NuElements v1, adding a touch of semi-realism and stronger edges to the mix.

Drawing from EtherBluMix5, KasyElements captures the characteristic allure of painted anime—a world full of wonder and vibrant imagination. Yet, with the influence of NuElements v1, this artistic realm is grounded with a sense of authenticity. Characters come alive, not just within their animated universe but with a resonance that feels closer to our reality.

Also I want to point out that this is my first Checkpoint (and merge) and I might try making better ones in the futures.

Strengths of the Model:

Close up portraits and generally all strengths that EtherBluMix brings.

Weaknesses of the Model:

NuElement has a weakness with Eyes at a distance, which also affects KasyElements.

Recommended settings:

This model already includes the kl8-f8-anime2 VAE so you do not need to add a VAE.

I might add a vanilla version in the future.

You can check out the recommended settings of EtherBluMix. But you can also test out the following recommendation from my images and tests:

Sampler: DPM++ 2M Karras
Steps: 20 - 28
CFG: 6 - 9
Clip Skip: 2
Denoising strength: 0.4 - 0.6

I personally use 540x675 and scale up 2x with R-ESRGAN 4x+Anime6B.

But you can take any formats from 512x512, 512x768 or other recommended SD1.5 setups.

Prompting recommendations:

The same as with EtherBluMix and NuElements I recommend the anime/fantasy/illustration specific positive and negative prompts.

Positive: masterpiece, best quality

Negative: NSFW, (worst quality, low quality:1.3)

But you can also anytime check out my posted images, since I never upload images without providing the full prompt.

Loras and other:

I use a lot the "Add more Details" Lora by Lycon these days. I recommend playing around with between 0.5 and 0.75 as too many details sometime makes the image too cluttered, but you can use the model without any Lora and get amazing close up images.

Credits:

EtherBluMix by gamerdan69

Great model, my most favourite painting style anime model.

NuElement by Ocean3

You merged some cool stuff here and I enjoy using it every second day!
Add More Details by Lycon

Love this Lora since it adds the small touch that I usually miss when not using this Lora!

Model Creation:

Main Model 0.7 : EtherBluMix by gamerdan69

Secondary Model 0.3 : NuElement by Ocean3

Added VAE: kl-f8-anime2 VAE by Tony

License & Use

This model is open access and available to all, with a modified 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(s) Stable Diffusion and Dreamlike Diffusion 1.0.

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).
- To generate NFTs

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.