Diffusion XL

TL;DR: Enter a prompt or roll the 🎲 and press Generate.

Prompting

Positive and negative prompts are embedded by Compel for weighting. See syntax features to learn more and read Civitai's guide on prompting for best practices.

Arrays

Arrays allow you to generate different images from a single prompt. For example, [[cat,corgi]] will expand into 2 separate prompts. Make sure Images is set accordingly (e.g., 2). Only works for the positive prompt. Inspired by Fooocus.

Styles

Styles are prompt templates from twri's sdxl_prompt_styler Comfy node. Start with a subject like "cat", pick a style, and iterate from there.

Scale

Rescale up to 4x using Real-ESRGAN from ai-forever.

Models

Each model checkpoint has a different aesthetic:

cagliostrolab/animagine-xl-3.1: anime
fluently/Fluently-XL-Final: general purpose
SG161222/RealVisXL_V5.0: photorealistic
stabilityai/stable-diffusion-xl-base-1.0: base

Advanced

DeepCache

DeepCache caches lower UNet layers and reuses them every Interval steps. Trade quality for speed:

1: no caching (default)
2: more quality
3: balanced
4: more speed

Refiner

Use the ensemble of expert denoisers technique, where the first 80% of timesteps are denoised by the base model and the remaining 80% by the refiner. Enabled by default. Not available with image-to-image pipelines.