Welcome to NAIAD!
This is an NAI / Illustrious merge with a bunch of hand-selected checkpoints and LoRAs to improve the base model's realistic capabilites.
And wow, does it deliver!
It's focus is on creating creative and fun fantastical images of high quality, photorealistic, but exaggerated images with a focus on women.
To use the faster low-step settings, you need to use the DMD2 LoRA. This allows you to use 8 or 16 steps and generate very fast. Remember to generate in 2 passes, either using "Hires fix" in Forge/A1111, or by creating and chaining a second sampler node in ComfyUI. A sample workflow if included in the sample images of the model. Use this as a reference.
Each sample/preview image contains the used workflow. Here's a quick article with simpler more beginner-friendly workflow. This is a recommended starting point.
Recommended Settings
Base Generation
Steps: 24
CFG-scale: 3
Sampler: Euler_A
Scheduler: Karras
Upscale/Refine
Steps: 8
CFG-scale: 3
Sampler: Euler_A
Scheduler: Karras
Denoise: 0.35
Description
FAQ
Comments (6)
I think something's missing in the model, using euler_a/karras at 30 steps, 3 - 7 CFG generates a very washed out, sepia image.
It works fine for me. Otherwise try "Simple" instead of Karras. And maybe try with the dmd2 LoRA as well for lower CFG.
The model is a bit desaturated by itself, so it's not unexpected. But you should be able to get decently saturated images like the sample generations at least.
@6tZ Yup, confirmed it requires the use of the DMD2 lora: https://civitai.com/models/1608870?modelVersionId=1820705
Otherwise images come out washed out.
Use of DMD2 lora is required, or bumping CFG to 9.
Great model, love the name. Very civilized
Thank you! It's one I hope to get back to at some point. Such a strong foundation with prompt understanding. But hard to wrestle into submission realistic style-wise.
Currently busy with Z-Image though.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.