|
--- |
|
datasets: |
|
- opendiffusionai/laion2b-45ish-1120px |
|
- opendiffusionai/laion2b-squareish-1024px |
|
- opendiffusionai/laion2b-squareish-1536px |
|
--- |
|
|
|
# What is this? |
|
This is not a permenantly released model. More like an open alpha release. |
|
|
|
## Latest: 2025/03/01 |
|
|
|
XLsd32-dlionb16a8-phase1-LAION-e2.sft |
|
|
|
SD1.5 base, with the SDXL VAE tacked on, and then retrained to actually WORK. |
|
|
|
I think that this has reached parity with existing SD base. I'm going to keep training, but wanted to share what I had so far. |
|
|
|
# How to use |
|
Use it like any other SD1.5 model |
|
|
|
# How it was trained |
|
|
|
This is an fp32 model, trained with full fp32 precision, finetuned on a single 4090. |
|
|
|
The current version was trained on: |
|
- opendiffusionai/laion2b-45ish-1120px,moondream captions |
|
- opendiffusionai/laion2b-45ish-1120px, wd14 captions |
|
- opendiffusionai/laion2b-squareish-1024px, moondream captions |
|
- opendiffusionai/laion2b-squareish-1536px, wd14 captions. |
|
|
|
The 1024px was a mistake: i meant to use the 1536px. but by the time I noticed it, it was 2 days in, and I thought "what the heck, let it run" |
