RobMix CosXL

This is a CosXL checkpoint. Read before you download.

From the Stability CosXL HuggingFace

"Cos Stable Diffusion XL 1.0 Base is tuned to use a Cosine-Continuous EDM VPred schedule. The most notable feature of this schedule change is its capacity to produce the full color range from pitch black to pure white, alongside more subtle improvements to the model's rate-of-change to images across each step."

In my early tests, the CosXL base model was already fantastic, but I wanted to merge in some of my recent SDXL checkpoint merges to give it a bit more, je ne sais quoi.

Pros and Cons

Pros:

• Unparalleled contrast

• Super sharp

• Seems to have more interesting compositions and diversity than SDXL

Cons:

• Super touchy with CFG. If you go beyond 4.0, expect artifacts, even with rescale

• Limited subject knowledge

How to use CosXL checkpoints

As of the time I'm posting this, ComfyUI and StableSwarmUI support CosXL out of the box. I have not heard of support for other web UIs.

For finer control of the contrast and detail, add a ModelSamplingContinuousEDM node to the model pipeline and adjust your sigma_max and sigma_min settings.

Don't quote me on this, but I understand those to represent the max and min amount of noise that can be removed from the image in each step.

Raising sigma_max adds more contrast to the image, but overdoing it tends to burn the image a bit. It seems 120 is standard, I like slightly higher values.

You can lower sigma_min to absurdly low values, but I find that anything below 0.0001 or anything above 0.1 result in obvious artifacts.

Recommended Settings

Download the example ComfyUI workflow here.

This model significantly benefits from a second pass (hires fix).

First Pass

• 40 steps

• CFG 3.0-4.0

• DPM++ 3M SDE Karras

• sigma_max 200

• sigma_min: 0.002

Second Pass

• 1.5x latent upscale

• 0.3-0.4 denoise

• 20-40 steps

• CFG 3.0-4.0

• DPM++ 3M SDE Karras

• sigma_max 50

• sigma_min: 0.001

I find lowering sigmas in the second pass helps a lot with fine details and produces really, really crisp images.

For an added bonus, you can add the following:

• FreeU

  • B1: 1.05

  • B2: 1.08

  • S1: 0.95

  • S2: 0.88

• Self-Attention Guidance

  • scale: 0.5-0.8

  • blur_sigma: 2.0-4.0

• CFG Rescale: ~0.3