Skip to content
Other

WAI-illustrious-SDXL GGUF

quantized image generation model

1 min readupdated

This repository provides the popular WAI-illustrious-SDXL checkpoint (a model weights file for generation) converted to the GGUF format (a model weight compression format that saves memory). The model is optimized to run on GPUs with limited VRAM (video memory) without significant quality loss. It generates detailed images in anime and artistic styles. Built on the SDXL architecture, it is designed for use in interfaces like ComfyUI that support GGUF.

Key features

  • Available in Q4_K_M, Q5_K_M, and Q8_0 quantizations for different memory budgets
  • Optimized to run on GPUs with low VRAM
  • Improved character accuracy and clean visual style
  • Compatible with ComfyUI-GGUF nodes

What you can do

  • Generate detailed anime-style illustrations and artwork in ComfyUI
  • Run the model on PCs with modest hardware specs thanks to GGUF compression
  • Generate at resolutions of 1024x1024 and higher to match native quality

Example

To run it in ComfyUI, place the model file in your ComfyUI/models/unet/ folder and use the recommended settings: CFG scale 4.0 - 6.5, Sampling steps 25 - 35, and the Euler a sampler.

Read moreDetails
Formats: Q4_K_M (~5-7GB), Q5_K_M (~8-10GB), Q8_0 (original size)
Requirements: requires ComfyUI-GGUF to be installed
Notes: VAE is baked into the model
Discuss Telegram 0 27

Will it run?

Runs in GGUF Q8_0

The most precise of the ready quantised files fits.

  • GGUF Q8_0recommendedweights 2.5 GB · ready files3.3 GB
  • GGUF Q5_K_Mweights 1.6 GB · ready files2.3 GB
  • GGUF Q4_K_Mweights 1.3 GB · ready files2.0 GB

Tip: go 8-bit.GGUF Q8_0 is within about a percent of full precision in quality, takes half the memory and runs faster on RTX 40/50 and H100. Full precision only pays off for fine-tuning.

What to get for this model

Massed ComputeOpen Massed Compute

Your own GPU: GGUF Q8_0 — from RTX 2060

Massed Compute hourly prices, November 2026. The discounted price applies with the coupon at checkout.

Estimate: weights plus working memory. Long videos, high resolutions and long contexts need more.

Run it on Massed Compute

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    # tiondoubl/wai-illustrious-sdxl-GGUF
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download tiondoubl/wai-illustrious-sdxl-GGUF --local-dir ~/models/wai-illustrious-sdxl-GGUF
    # The model is in ~/models. How to run it is in the model card (link above).
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (2)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

Model family

New posts about versions of wai-illustrious-sdxl-GGUF (quants, finetunes, LoRAs) will show up under the bell.

No known relatives of this model yet. All derivatives on Hugging Face

About the model

tiondoubl/wai-illustrious-sdxl-GGUF
Author
tiondoubl
Category
Other
Released
Posted

On NeyroLearn

Hugging Face

270

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments