CivArchive
    8Buff_Gen - v1.0
    NSFW
    Preview 505206
    Preview 505204
    Preview 505205
    Preview 505197
    Preview 505202
    Preview 505227
    Preview 505214
    Preview 505215
    Preview 505216

    NEW! No_EMA Pruned version now available!

    We are proud to announce that Eight Buffalo Media Group has shared our first text-to-image model!


    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.

    See images for prompt matrix testing.

    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.

    Current known issues/limitations:

    • More people you add, the more likely you will get blurry/distorted faces

    • Tends to make women young looking. Add negative prompts to help this.

    • Tends to make men old looking. Add negative prompts to help this.

    • When putting people in jars, faces tend to be blurry/distorted. The more jars and more people, the more blurry/distorted. Prompts and and restore faces can help this a little. 

    • DPM++SDE Karras sampling method tends to get the best consistent results, but experiment.


    Going for a general purpose model with a fine level of control. Merged with a lot of different models, but don’t remember all of them. Links below to those that were remembered or provided inspiration for direct training.

    Please review and respect any related licenses. See https://huggingface.co/stabilityai

    Common Negative Prompts Used:

    (((worst quality, low quality, bar censor, distorted face))), (((jpeg artifacts, signature, watermark, text, username))), blurry, bad faces, blurry 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,

    See our page on huggingface: https://huggingface.co/EightBuff/8Buff_Gen

    Our Blog is now live! Check it out for the latest news and articles: https://eightbuff.blogspot.com/

    Shop our RedBubble page and help our artists.

    Subscribe to our Patreon Site for News and updates! 

    Buy us a Coffee! https://www.buymeacoffee.com/eightbuffalo

    http://eightbuff.com

    Enjoy!

    Description

    V1 - Current known issues/limitations:

    • More people you add, the more likely you will get blurry/distorted faces

    • Tends to make women young looking. Add negative prompts to help this.

    • Tends to make men old looking. Add negative prompts to help this.

    • When putting people in jars, faces tend to be blurry/distorted. The more jars and more people, the more blurry/distorted. Prompts and and restore faces can help this a little. 

    • DPM++SDE Karras sampling method tends to get the best consistent results, but experiment.

    FAQ

    Comments (2)

    MirabilisApr 16, 2023· 3 reactions
    CivitAI

    Very cool. Though I dare say people would appreciate a pruned version if possible. 7GB is on the large side.

    Wortwood1Apr 17, 2023· 2 reactions
    CivitAI

    Agree about needing a prune. Decent model, hope to see it improve.

    Checkpoint
    SD 1.5

    Details

    Downloads
    393
    Platform
    CivitAI
    Platform Status
    Available
    Created
    4/15/2023
    Updated
    5/11/2026
    Deleted
    -
    Trigger Words:
    person_in_Jar

    Files

    8buffGen_v10.ckpt

    Mirrors

    HuggingFace (1 mirrors)
    CivitAI (1 mirrors)

    8buffGen_v10.safetensors

    Mirrors

    HuggingFace (1 mirrors)
    CivitAI (1 mirrors)

    Available On (1 platform)

    Same model published on other platforms. May have additional downloads or version variants.