If you enjoyed this model, why don't you check out my other works? I put a lot of effort into correctly recreating artist styles and making the occasional character LoRA.😊

You can also buy me a Coffee ☕ at https://ko-fi.com/stickyricky

This model was trained using the collab/guide by holostrawberry [Guide] Make your own Loras, easy and free - colabs | Stable Diffusion Other | Civitai

There already exist other LoRAs for this style on civitai and huggingface. I recommend that you compare them yourself, check the recommendations below.

I attempted to make this model consistent. No random monochrome images, broken ??????? or fragmented/panelled outputs.

About the artist:

Pixiv Fanbox: spray and pray - pixiv

Twitter: ratatatat74 (@ratatatat74) / Twitter

Patreon: Ratatatat74 | Creating painting | Patreon

Ratatatat74 is in large part a hentai artist, so you can expect the occassional ?????? even when not specifically prompted. Their unique comic style is defined by often rough and angular linework and limited color palletes accentuated by strong shading.

For the more detailed art there is a general shine to the characters and women are almost always blushing.

Finally, a large part of their content is fanart with characters from MHA (Mirko in particular) and LoL

Weights & Prompts

pruned:

This should be your goto model if you do not want sketch style art.

Use a weight of .8-1.2. I just used 1.0. Adjust to taste and depending on your checkpoint.

Check the XYZ plot for reference.

Note that the activation prompt for this version is just:

ratatatat74 

Because of the smaller dataset you can also expect a pretty consistent representation of Mirko with the right prompts. Try:

 long hair, large breasts, animal ears, white hair, thighs,  dark skin,  rabbit ears,  dark-skinned female, parted bangs,  muscular,  rabbit girl, muscular female, long eyelashes

The example images are almost exclusively redone images of the former versions for easy comparison - with some small changes to get the originally intended result.

For the other two versions the only necessary prompt is

ratatatat74_style 

although it mostly gets there even without prompts.

NAI:

Use a weight of 1.0, adjust to taste.

AOM:

Use a weight of 1.0, adjust to taste. This model is really flexible and is compatible with other LoRA (character or pose models) at full weight. As usual I have included an XYZ plot.

For inspiration check the examples. I heavily recommend experimenting with the steps as well. Sometimes a 12 step image is just what you want, sometimes it takes 30 to get the necessary detail.

It might be worth experimenting with some stylistic prompts that are baked in. Some possible options are

sketch, lineart

Please leave a review if you enjoyed this model or have problems with it. I'd also be interested in how the model behaves with other base checkpoints, so why don't you give it a try and throw some images down below! 👇