✅ Positive Prompt for Illustrious
Stable_Yogis_Illustrious_Positives
🚫 Negative Prompt for Illustrious
Stable_Yogis_Illustrious_Negatives-neg
==========================================================
✅ Positive Prompt for SDXL PONY
Stable_Yogis_PDXL_Positives
🚫 Negative Prompt for SDXL PONY
Stable_Yogis_PDXL_Negatives-neg
⚠️ Please use this model responsibly. While it is designed for high-quality and artistic outputs, AI generations can sometimes produce unpredictable results. I bear no responsibility for any unintended outputs—experiment and tweak settings to match your needs!
Description
Sampling Method: Euler a
Sampling Steps: 5+
Resolution: 896x1152 / 832x1216
CFG Scale: 1
Clip Skip: 2
This is 4 step model, only use Euler A with CFG 1
FAQ
Comments (3)
no description, no use ?!?
i mean ... ??? merge ? train ?
what is should be better from v1 / v2 ???
50% of images have typical "long body" issue, which was solved ages ago even for SD1.5 checkpoints. How you managed to break Pony and IL which usually draw prefect bodies? Is it result or yours "special training"? Is so, you did it wrong.
Another issue - cloned pubic hair, It exactly the same on all images, like same fragment photoshopped. Did you use 1 image dataset?
aimrimPonyIllusSDXL_v10ILLFP16
🙏