We are proud to announce that Eight Buffalo Media Group has shared our first text-to-image model! This Stable Diffusion 1.5 model is a combination of many different models that have been mixed, merged, and specifically trained on a couple things like people in glass jars. The goal is a strong general model that allows control similar to many anime models, with a more realistic look and feel. Check out the images and videos!

Available for use or download from: https://civitai.com/models/41928/8buffgen or https://huggingface.co/EightBuff/8Buff_Gen 

This Stable Diffusion 1.5 model is based off of the 8Buff_Gen model, different models that have been mixed, merged, trained and adjusted weights. This model does require a good deal of prompt crafting, the trade off is you have a lot of control on the images you create. I would recommend finding a prompt that generates the style and quality to your liking and saving it as a style. Check out the images and videos made with this model!

Available for use or download from: https://civitai.com/models/118761/8buffreal and https://huggingface.co/EightBuff/8Buff_Real 

This Model is a mix of our Gen and Real SD 1.5 models, with some additional training and adjustments for improved hands and prompts. Note that Version 1 of this model still has a few issues, so please be patient as we improve. This model does require a good deal of prompt crafting, the trade off is you have a lot of control on the images you create. It has a focus on multiple people and of different looks and ages, with prompts of elderly or 60_years_old. It will also do nationality or skin color.Very stable with images for short video and GIFS, see below for samples. 

Available for use or download from: https://civitai.com/models/479886/8buffmix and https://huggingface.co/EightBuff/Mix

Our 8Buff_XL models are tuned, mixed, and trained our model to improve the image quality, diversity, and consistency. Our models tend to focus on the generation of multiple people. Use terms Woman/Man for singular, and Men/Women for multiple. You can provide a number (3Men) or specify a line of people (line of cheerleaders) also. Stating things like ‘people in background’ will provide people and crowds, but will often be blurry and less defined. To generate different skin colors and looks, you can use countries names or geographic regions such as; Nigeria, European, Canadian, Japanese, ect… Use terms like Man/Woman for adults, girl/boy for younger people. When creating groups of people that should look different from one another use positive prompt terms such as; different face, different hairstyle, different body type, etc. To enforce this you can also use negative prompts; same face, same clothes, etc…

Available for use or download from: https://civitai.com/models/221036?modelVersionId=249281 and https://huggingface.co/EightBuff/8BuffXL_v1