This is a cool little merge project. Does really well in SFW haven't done any NSFW testing but should be just fine.
There are 2 different models with different baked VAEs. They are both great and work well, but feel free to test them out and find which you like the most!
I recommend using Euler a, as the DPM ++ samplers tend to mess with the faces. You can totally fix this with a little inpainting as the rest of the images look totally fine.
IMPORTANT:
To properly generate furry characters, I highly suggest adding the tags:
"|species| |gender| furry", "anthro", "fursona", "anthropomorphic", "(|color| fur)".
Just put whatever species, gender, color, etc. you want. Without these the model tends to do more anime and monstergirl type gens. The fur color helps prevent skin color being human and it just brings a solid and more fur like color and texture to the images.
This model does require some inpainting to get what you want.
Sevens Mix [Furry Model] is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user pipe. Derived from the powerful Stable Diffusion (SD 1.5) model, Sevens Mix [Furry Model] has undergone an extensive fine-tuning process, leveraging the power of a dataset consisting of images generated by other AI models or user-contributed data. This fine-tuning process ensures that Sevens Mix [Furry Model] is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as anime, cool, lighting.
With a rating of 4.86 and over 7 ratings, Sevens Mix [Furry Model] is a popular choice among users for generating high-quality images from text prompts.
Yes! You can download the latest version of Sevens Mix [Furry Model] from here.
To use Sevens Mix [Furry Model], download the model checkpoint file and set up an UI for running Stable Diffusion models (for example, AUTOMATIC1111). Then, provide the model with a detailed text prompt to generate an image. Experiment with different prompts and settings to achieve the desired results. If this sounds a bit complicated, check out our initial guide to Stable Diffusion – it might be of help. And if you really want to dive deep into AI image generation and understand how set up AUTOMATIC1111 to use Safetensors / Checkpoint AI Models like Sevens Mix [Furry Model], check out our crash course in AI image generation.
Baked with the orangeabyss VAE. Solid and slightly more "dreamy" and slightly less saturated images.