Description

SDXL + Pony

NOTE: USE THE SDXL CLIP VERSION FOR SDXL TRAINED CELEBRITY'S - The Pony CLIP version has slightly better PONY characters at the cost of SDXL names triggers.

Currently the FP32 version is exclusive to TensorArt

• It is a 11B parameter training distilled to allow a perfect blend of SDXL and PONY while using SDXL CLIP

• You can use SDXL named celebrity's or PONY characters

• SDXL LORA's preferred over PONY

• Should work with SDXL control nets as the model was quantized from FP32 CLIP-L and CLIP-G

• The diffusion (UNET) model will work with either SDXL or PONY CLIP-G and CLIP-L

Why 51/50 because 51/49 does not sound good, even if it is more accurate.

sampler: DPM++ 2M Karras

steps: 20

CFG: 6

not my model, i take no credit. all credit goes to creator @ https://civitai.com/models/1562969?modelVersionId=1768974