ULtraReal 2 (SuperModel Edition)

Full Checkpoint do not load additional CLIP or VAE

• This model uses FP32 Timestamp training

• Realistic Faces and Characters across 100's of PONY trainings

• Full FP32 precision (UNET can be downcast with no issues)

ULtraReal 8GB PONY

Full Checkpoint do not load additional CLIP or VAE

Version 1 is 12GB and Full FP32 but has issues with faces

Version 2 Fixed Faces - Hybrid is BF16/FP32 - Lite is FP8/FP32

• This model was trained using FP32 precision with a focus on realism

• The hybrid version is 8GB but will run as fast as base PONY

• FP32 CLIP is as fast and superior to FP16 in 99% of cases (CLIP is handled in CPU)

• This model is intended for use with up-scaling (See images for workflow)

This model uses FP32 CLIP these commands should be used, this will not slow down your IT's unless you have very low system RAM

• Comfy UI --fp32-text-enc

• Forge/Auto1111 --clip-in-fp32

---

• All images should be repeatable when loading the source image.

• Note I normally try and credit image remix if you see "your" prompt in comment below and I will link your image.

描述:

Improved Faces - Reduced UNET to BF16

训练词语: