Alma Experimentals

CHECKPOINT
Original


Updated:

I've decided to upload experimental models here. They're models that have some issues or weren't quite what I was aiming for but aren't bad so I don't want to delete them. I'm uploading here because they can still make good images under the right conditions and some of them might be especially good for certain niches.

I post updates about what I'm working on at https://ko-fi.com/almascar you can also support me there ;)

Version Detail

Pony
Suggested parameters: No baked VAE, use XL_VAE_C c9.1 for vibrant colours. Sampler and Scheduler: Euler A SGM Uniform Steps: 20-40 CFG: 4 Use Face Detailer and Highres Fix as needed. DAT-4x upscaler 0.4 or lower denoise for face detailer and highres fix Many other settings will work above are just my preferences for style and gen time. This is a MBW merge of BeMyPony-SemiRealAnime and One-Trick PonyXL v2.0 that was an intermediate step in making Alma Realistic PDXL v1 and v2 so this is pretty much v0 for Alma Realistic PDXL. This makes realistic style images with detailed backgrounds and good knowledge of fantasy and science fiction concepts. Compared to v1 and v2 of Alma Realistic PDXL it's a little more predictable but a bit worse at anatomy. I post updates about what I'm working on at https://ko-fi.com/almascar you can also support me there ;)

Project Permissions

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated contents

  • Use on generation services

  • Sell this model or merges

Related Posts