Our latest 8Buff SDXL Model 8Buff_XL_v2 has been released!Model notes and prompt suggestions:<ul><li>Based on our 8Buff_XL_V1 model, we have fine tuned, mixed, and trained our model to improve the image quality, diversity, and consistency.</li><li>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.</li><li>To generate different skin colors and looks, you can use countries names or geographic regions such as; Nigeria, European, Canadian, Japanese, ect…</li><li>Use terms like Man/Woman for adults, girl/boy for younger people.</li><li>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…</li><li>Training done primarily on 1024x1024, 1024x1280, and 1280x1024 images. When mixing with LORA(s) recommend starting with 1024x1024 and adjusting from there.</li><li>Sampling method that provides the most consistent results is DPM++ 3M SDE Karras (in Automatic1111). Any of the Exponential methods tend to generate more refined images but less consistency.</li><li>Known issues:<ul><li>Some sample methods tend to paint color streaks over pictures.</li><li>Perspective, hands, and eyes are still issues, like most models. Using seed and variation adjustments can help address some of these.</li><li>It is biased and tends to be a little thirsty at times. Be selective with your prompts.</li><li>Still very bad at spelling, but you can do basic text with prompts like, small sign with handwritten text ‘eightbuff’, with the text you want between the ‘ quote' signs.</li></ul></li></ul>Works well with LORAs.Check out our blog <a target="_blank" rel="ugc" href="https://eightbuff.blogspot.com/">https://eightbuff.blogspot.com/</a> for more details.

8Buff_XL

v1 of our 8Buff XL model. It is a mix of of mixing and training focused on multiple people in realistic images. While it's not quite perfect at photorealism, and might struggle a bit with super complex scenes or hands, our focus was to make is possible to easily prompt for multiple people.Does well with 'DPM++ 3M SDE Karras' at 1024x1024 for most people.Works well with LORAs.

Files with SHA256: 7e06026f57720130b2a97bdcdcf2b7b454ff67edc5868dfaa5c7da75e771da21