💚 for Updates - I would love to see your reviews and images of this model, feel free to post them below!
💡 Version 1 - first version, soft anime aesthetic with some creativity and detail.

Model Series: (ne series)
Status: ongoing

🤗 view more on Hugging Face

This model keeps surprising me and currently reigns as one of my favorites generally speaking as well as among my unreleased/released models. I made this mix one day after experimenting with some other merges using MBW. I essentially started with an uncommon base and used some common to uncommon weight presets testing by eye merging in aspects of models as I went.

The final result really brings together some of the styling I enjoy in a neutral fashion. Some great detail, great texture and lighting/reflections, semi-soft/muted tones, and an overall mostly-stable creative flexibility with prompts and configurations across the board. Hopefully you enjoy this one as much as I have ~ feel free to let me know!

💡 Alternate versions and more information can be found on the Hugging Face page.

General Use

I've found this model to be decently flexible - use the parameters you find best.
The preview image and gallery sections can give you a good base as a starting point. Start simple, then go from there.

Be keen of any conflicting styles and how tokens may 'lean' the model toward one style or another. Some prompts may be a bit messy, but overall should be able to be toned down or reworked. For a soft/neutral anime style, keep prompts from being too heavy on realistic style tokens. You can enhance an anime style (or others) with related terms such as anime, 2d, flat color, outlines, etc.

~20 steps, 7 scale, ~0.4 denoising, clip skip 1 or 2, is a good starting point

Tips

This model currently loses a bit of clarity/detail with eyes at a mid-far to far character distance depending. This can be remedied at times by either changing your prompt to exclude certain tokens such as full body and/or upscaling the image once again using the img2img upscaler. Hires fix upscale initially is already assumed to be used.

📝adetailer can also be a great way to fix/add detail to characters that are at a mid to long distance, and would otherwise have issues with accurate details. This tool can be utilized in a number of different ways. However, I don't recommend using adetailer all the time. I have had results either be enhanced/corrected or be altered away from a good result.

Hands/fingers are generally passable. Try to tweak your parameters/prompt if you're having issues. This model is powerful, but not perfect. A high hires fix denoising value, your upscaler choice, etc. may cause some issues at times. You can also take a look at various negative embeddings to mitigate any issues.

Samplers

I've found a lot of samplers work great being fairly similar across the board with this version. Have fun and try some common and uncommon configurations.

VAE

Use whichever VAE you find best. Included is a renamed vae-ft-ema-560000-ema vae (SuperMixA.vae). Models containing a baked-in VAE, found on the Hugging Face page, are listed as -bv or -bakedVAE making the use of a VAE file redundant.

vae-ft-mse-840000-ema and ClearVAE_V2.3 can also be good options.

Keeping things simple for now. I might add to this page including some simple prompt presets or so if I decide to update or add anything.

Note: this version/model is not finetuned to maximum detail accuracy.

Disclaimer

This model(s) may output NSFW content unintentionally depending on parameters used. Make sure you tailor your prompts accordingly. For example "nsfw" in the negative prompt.

The purpose of sharing this model is not to showcase obscene material in a public forum. The use of this learning model is entirely at the discretion of the user, and they have the freedom to choose whether or not to create SFW or NSFW content. The decision of whether to engage with SFW or NSFW content lies with the user and their own personal preferences. The ai model(s) do not contain explicit visual content that can be accessed easily.

Example Images used

vae-ft-ema-560000-ema vae
4x-UltraSharp or R-ESRGAN 4x+ Anime6B upscalers
hires fix w/ some upscaled again using SD upscale
use old karras scheduler signmas (0.1 to 10) compatibility setting
any LoRa use should be listed in the image metadata
Bad_v2 negative embedding renamed should be the same as bad_prompt_version2
EasyNegative and badhandv4 negative embeddings were also used

*Negative embeddings are optional

Resources

This model merge (v1) used the following resources - all of these are great stand-alone, props to each creator.

FeelYou_a2 (removed, iirc was via Bradcatt)
Counterfeit_v3 (via rqdwdw)
Pika's New Generation_v2 (via PikaDesigner)
SuperMix
Dark Sushi Mix-Darker (via Aitasai)
GyozaMix_v3 (has a lot of great aspects, especially in mixes!, via Jemnite)
Rev Animated_v1.2.2 (via s6yx)

📝 A full recipe can be found on the Hugging Face page

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.

Note: this model should be able to be updated to not include the Dreamlike Diffusion licensing fairly simply. I may do so in the future.

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.

Note

If you see any conflicts or corrections to be made, please let me know.