Sign In

SDXL 4GB/2GB (Improved FP8 & GGUF)

Download

1 variant available

fp8 SafeTensor

SDXL_FD-FP8.safetensors

8-bit, smaller file • 4.07 GB

Verified:

Type
Checkpoint Merge
Stats

1,488

318

Reviews
Published

Oct 19, 2024

Base Model

SDXL 1.0

Training
Steps: 100,000
Epochs: 10
Usage Tips
Clip Skip: 1
Hash
AutoV2
82D1376526
default creator card background decoration
Reactions - 63866

63.9K

Downloads - 590605

590.6K

Generations - 4893664

4.9M

SDXL Training Contest Participant
ComfyUI_00245_.png

SDXL 4 Step (FP32 with Improved UNET)

  • Note I used the 32bit CLIP-G

  • Refiner used in workflow also 32bit GGUF

  • Updated CLIP-L

  • For 4 Step use at CFG 1.0 - Load a image for workflow

  • For NSFW images the refiner should not be used

  • BRSGAN 2x can be found on Google Drive

2GB GGUF from FP32

Note 2GB requires separate clip and GGUF support, 4GB FP8 is ready to use in any SD GUI

  • Refined with baked FP32 Lora's

  • Quantized from the FP32 SDXL model for less loss

  • For GGUF Download separate SDXL CLIP-G and CLIP-L and VAE

4GB SDXL (Full Checkpoint)

  • Custom CLIP is not Quantized

  • Custom UNET quantized to FP8 allowing for a balance of size and quality

  • Works in FORGE, Comfy-UI and Auto-1111

  • Works with LORA's

  • Beta/Deis is a good choice for img 2 img up-scaling

Both models have improved anatomy (Uncensored) for females however GGUF version does not do well with males.