Pro version of Babes_By_Stable_Yogi Pony is available on my Patreon
Onsite generations are permanently available on this version:
๐ 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.
## ๐ 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: 25โ30
- CFG: 5โ7
DMD2 variant only:
- Sampler: LCM
- Steps: 4 (yes, four)
- CFG: 1.2
Resolution: native SDXL โ 1024ร1024, 832ร1216, 1216ร832 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.
๐ Like this model to keep me motivated and inspired to create more!
๐ฌ Drop a comment and let me know what you'd love to see next.
๐ Review this model to help me improve and make even better creations.
๐ Hit that notification bell to stay updated with my latest models and updates!
Important Usage Tips
Add Stable_Yogis_PDXL_Positives at the beginning of your prompt section.
Add Stable_Yogis_PDXL_Negatives-neg at the beginning of your negative prompt section.
Description
This version introduces enhanced detail and depth, with training focused on:
Natural environments and background variety
Improved lighting and shadow control
More accurate anatomy, including hands and body structure
Balanced NSFW and SFW generation capabilities
Stronger prompt adherence for precise results
โ๏ธ Recommended Settings
Steps: 20+
Samplers: Euler a, DPM2a, DPM++ SDE Karras, DPM++ 2M SDE Karras
CFG Scale: 4+
Resolution: Fully SDXL-compatible sizes
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)
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.
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.
very versatile with loras
whats the difference between v5 & v5-4s ???
v5 is regular model and & v5-4s is a 4 step version ( Lightning version based on DMD2 for faster image generation )
@Stable_Yogiย thank you ๐
If thereโs another model/version youโd like to generate images with, just place a bid here and Iโll make it available for onsite generation:
https://civitai.com/auctions/featured-checkpoints
very inconsistant
Best Pony related model out there. I have tried them all. The amount of details is incredible. Thx a lot!
๐๐
Fds vadia me mostra logo a bct peluda
enable v5 for onsite generation pls
Sure, To keep this model up for generation, please bid at least 2000 Buzz every week.
The guy that makes 40,000+ buzz per day wants you to spend yours...
J1Bย Hey J1B ๐
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 2โ3 variants from each โ thatโs 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 โ40K buzz per dayโ without full context doesnโt help anyone โ especially when it's used to suggest others should carry the weight. Letโs focus on building up the space, not stirring unnecessary comparisons.
Letโs grow together, not gatekeep or undermine. Wishing you more success ahead ๐



















