Tensor.Art
Create

WAI-illustrious-FP8 - Mix-V16

WAI-illustrious-FP8

CHECKPOINT
Original

Updated:

Mix-V16
V16
WAI-illustrious-FP8 by MorikoMorizz on Tensor.Art
WAI-illustrious-FP8 by MorikoMorizz on Tensor.Art
WAI-illustrious-FP8 by MorikoMorizz on Tensor.Art
WAI-illustrious-FP8 by MorikoMorizz on Tensor.Art

This is a quantized version of WAI-illustrious-SDXL, Built-in VAE and CLIP included.

The default FP16 model can take up 6-7gb just to load vram and do image Diffusion. the Unet model only needs 4.8gb vram on KSampler / Processing Image.

ComfyUI Recommended

Base Model: https://tensor.art/models/943946051788787917/WAI-illustrious-v16

All credits to the original creator: https://tensor.art/u/762555264535746522

My Other Models : https://civitai.com/user/MorikoMorizz

Support My Work & Request Custom Quantization: It takes time, testing, and electricity to compress these models perfectly.

Got a specific heavy Checkpoint or LoRA you desperately need quantized for your PC? Drop a Potatos and your request here: https://ko-fi.com/morikomorizz

Version Detail

Illustrious
This V16 version uses FP8 for UNet, but the Text Encoder and VAE remain at FP16 for better context understanding and output quality.

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