CivArchive
    Preview 75877596
    Preview 75877588
    Preview 75877583
    Preview 75877589
    Preview 75877591
    Preview 75877592
    Preview 75877579
    Preview 75877581
    Preview 75877586
    Preview 75877575
    Preview 75877585
    Preview 75877578
    Preview 75877594
    Preview 75877582
    Preview 75877587
    Preview 75877577
    Preview 75877580
    Preview 75877590
    Preview 75877595

    Pro version of Babes_By_Stable_Yogi Pony is available on my Patreon

    Onsite generations are permanently available on this version:
    ๐Ÿ‘‰ Babes_By_Stable_Yogi: https://civarchive.com/models/174687?modelVersionId=2110984

    Babes By Stable Yogi V6.5

    V6.5 is a substantial step up from V6.0.

    Anatomy, Expressions and gestures, Environments, Pose stability

    A lot of these fixes came directly from feedback identified by our Patreon community โ€” folks running the in-development checkpoints, noting what broke, and helping us prioritize what to fix for the next version.

    ## ๐Ÿš€ Be part of the next version

    We run a free image generator at discord.gg/DZEenb5wGc that ships the next-in-development checkpoint inline. Explorers generate with it, report shortfalls, and we record that feedback into the build queue for the following version.

    If you've ever wanted to be part of how a checkpoint is actually made โ€” hop in. Free to use, no install, no setup. Generate, find issues, tell us, and you'll see your fixes land in the next release.

    ## File lineup

    Six format variants ship for general use:

    (FP16) | Default for most users โ€” best quality / speed balance |

    (BF16) | RTX 3000+ with BF16 support, slight speed edge |

    (FP8 Scaled) | ~8 GB VRAM cards โ€” Forge & ComfyUI native, no extra nodes |

    (NF4) | Lowest VRAM (4-6 GB) โ€” Forge native, ComfyUI with bnb_nf4 node |

    (Q6_K) | Highest quality GGUF โ€” needs ComfyUI-GGUF or [my Forge GGUF extension for forge ui] (https://github.com/brandulateai/sd-forge-sdxl-gguf-brandulateai) |

    DMD2 โ€” 4 steps, CFG 1.2, LCM sampler. Fastest option |

    ## Recommended settings

    Standard variants:

    - Sampler: Euler a or DPM++ 2M

    - Scheduler: Karras

    - Steps: 25โ€“30

    - CFG: 5โ€“7

    DMD2 variant only:

    - Sampler: LCM

    - Steps: 4 (yes, four)

    - CFG: 1.2

    Resolution: native SDXL โ€” 1024ร—1024, 832ร—1216, 1216ร—832 work cleanly.

    ## Where else to find me

    Pro variants and feedback: [Patreon](https://patreon.com/brandulate)

    (https://github.com/brandulateai)

    Free generator with the next checkpoint waiting for your feedback at Discord Community: https://discord.gg/DZEenb5wGc

    Join me on my Patreon. for exclusive perks and early access to unique resources.

    To discuss custom LoRa's or models, feel free to connect on Discord.

    • ๐Ÿ‘ Like this model to keep me motivated and inspired to create more!

    • ๐Ÿ’ฌ Drop a comment and let me know what you'd love to see next.

    • ๐ŸŒŸ Review this model to help me improve and make even better creations.

    • ๐Ÿ”” Hit that notification bell to stay updated with my latest models and updates!

    Important Usage Tips

    Description

    This is a Pony XL based on the DMD2 LoRA, designed for high-detail generations with improved accuracy and prompt control in just 4 to6 steps.

    Training in this version focused on:

    • Natural environments and diverse background styles

    • Enhanced lighting and shadow dynamics

    • Improved anatomical structure, especially hands and body forms

    • Balanced handling of both NSFW and SFW outputs

    • Stronger prompt adherence for more reliable results

    โš™๏ธ Recommended Settings

    • CFG Scale: 1 or 1.5

    • Steps: 6+ (8 for good quality, 10 for best results)

    • Samplers: Euler a, LCM

    • Resolution: Works with most Pony / SDXL resolutions

    Negative Embedding: Stable_Yogis_PDXL_Negatives-neg

    Positive Embedding: Stable_Yogis_PDXL_Positives

    I am happy to listen to your feedback, Share your thoughts, comments and relevant questions.

    Join me on my Patreon for exclusive perks and early access to unique resources.

    To discuss custom Lora's or models, feel free to connect on Discord.

    FAQ

    Comments (15)

    _degenerativeai_May 14, 2025ยท 15 reactions
    CivitAI

    It's been far too long since I've used an SDXL model for anything other than a refiner. I gave buzz for early access, but I'm seeing an issue that I believe is caused by having no VAE, or the wrong one. The images generated are washed out and blurry. Does this checkpoint have the VAE baked in? I can't seem to figure what I'm missing.

    _degenerativeai_May 14, 2025ยท 1 reaction

    I finally figured it out after looking at a few workflows people included with their images. My issue was I was missing the dmd2 lora.

    8333977May 18, 2025ยท 16 reactions
    CivitAI

    very versatile with loras

    mariedoll123May 20, 2025ยท 20 reactions
    CivitAI

    whats the difference between v5 & v5-4s ???

    Stable_Yogi
    Author
    May 20, 2025ยท 4 reactions

    v5 is regular model and & v5-4s is a 4 step version ( Lightning version based on DMD2 for faster image generation )

    mariedoll123Jun 2, 2025ยท 3 reactions

    @Stable_Yogiย thank you ๐Ÿ˜Š

    Stable_Yogi
    Author
    May 22, 2025ยท 12 reactions
    CivitAI

    If thereโ€™s another model/version youโ€™d like to generate images with, just place a bid here and Iโ€™ll make it available for onsite generation:
    https://civitai.com/auctions/featured-checkpoints

    PdidiJun 10, 2025ยท 25 reactions
    CivitAI

    very inconsistant

    AnandaAug 4, 2025ยท 12 reactions
    CivitAI

    Best Pony related model out there. I have tried them all. The amount of details is incredible. Thx a lot!

    Stable_Yogi
    Author
    Aug 4, 2025ยท 1 reaction

    ๐Ÿ™๐Ÿ˜Š

    6924666wsAug 4, 2025ยท 1 reaction

    Fds vadia me mostra logo a bct peluda

    nekoizmaseAug 9, 2025ยท 9 reactions
    CivitAI

    enable v5 for onsite generation pls

    Stable_Yogi
    Author
    Aug 9, 2025ยท 1 reaction

    Sure, To keep this model up for generation, please bid at least 2000 Buzz every week.

    J1BAug 18, 2025

    The guy that makes 40,000+ buzz per day wants you to spend yours...

    Stable_Yogi
    Author
    Aug 18, 2025ยท 3 reactions

    J1Bย Hey J1B ๐Ÿ‘‹
    I appreciate the passion โ€” you're a creator yourself, and I appreciate your work for the community.

    That said, please understand: I manage over 15 base models, each with multiple active branches. Users frequently request 2โ€“3 variants from each โ€” thatโ€™s over 10,000 Buzz/week per model just to keep things running for the community.

    So when someone asks for a variant to be enabled, I simply request them to support it with Buzz โ€” not because I need it personally, but because that's what keeps generation unlocked and accessible for everyone.

    Claiming โ€œ40K buzz per dayโ€ without full context doesnโ€™t help anyone โ€” especially when it's used to suggest others should carry the weight. Letโ€™s focus on building up the space, not stirring unnecessary comparisons.

    Letโ€™s grow together, not gatekeep or undermine. Wishing you more success ahead ๐Ÿ™