We are proud to announce that Eight Buffalo Media Group has shared our first text-to-image model!
Model Details
Note that Version 1 of this model still has a few issues, so please be patient as we improve. Constructive feedback is always welcome.
This freely available 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.
00321-573727474.png
Model Description
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.
General model, tends to be thirsty. Use negative prompts of NSFW to help control.
Recommendations
Tends to be overly sexy, nudity, skin color, and sexist. Working on correcting in future versions.
Common Negative Prompts Used-
worst quality, low quality, bar censor, distorted face, jpeg artifacts, signature, watermark, text, username, blurry, bad faces, bad eyes, bad anatomy, bad hands, error, extra limbs, missing fingers, extra digit, fewer digits, cropped, normal quality, missing fingers, extra digit, fewer digits, censor, black and white, monochrome, NSFW,
Training Details
Trained on images of shruken people and animals in glass jar, the prompt people_in_jar was used, but merging seems to have created issues. Will take prompts for shruken people in jars with consistent output.
