models/🥂🎆SDXL FaeTastic🎆🥂 - v1.6

🥂🎆SDXL FaeTastic🎆🥂 - v1.6

Faeia

8/8/2025

6:56:56 PM

| Discussion|

Related Keywords & Tags

Hyper detailed digital art of a jukebox user interface showcasing concentric circular design with bright blue and pink glowing elements, intricate switches, and metallic textures with volumetric and rim lighting effects.

Dark gothic underworld tower surrounded by spiked architecture and marsh mists with glowing blue and purple lights under a pink and blue sky.

A hyper-detailed cyberpunk hovering vehicle repair garage featuring a large central clock with glowing blue face and Roman numerals, surrounded by fiber optic lighting and sci-fi machinery.

A hyper-detailed digital artwork depicting a large celestial spiked wheel made of steel with vibrant pink and blue fluorescent glowing blades, set against a starry fantasy landscape with mountains and futuristic towers.

A hyper-detailed digital rendering of a decorated knight's Quantum Force Field Nexus surrounded by vibrant pink roses, glowing pathway lighting, and obsidian stone architecture.

A cyberpunk office with three silhouetted workers at computer stations, background features a futuristic cityscape with a giant moon, created using Stable Diffusion.

Futuristic cityscape with two astronauts standing under the full moon, AI generated using stable diffusion.

This AI generated image using Stable Diffusion depicts two futuristic explorers in space suits standing against a dramatic sci-fi landscape dominated by a massive, glowing celestial body and towering industrial structures.

A futuristic cityscape with silhouetted figures in the foreground, emphasizing a science fiction theme. This is an AI generated image using Stable Diffusion.

AI generated image using Stable Diffusion of a futuristic cityscape with silhouetted figures and a large structure under a moonlit sky.

A futuristic cyberpunk city scene with five standing figures, a large dome structure with bright light in the center, and towering buildings in the background generated using Stable Diffusion.

Futuristic cityscape with three silhouetted figures standing in front of a massive circular structure, AI generated using stable diffusion.

Recommended Parameters

samplers

Euler a, DPM++ 2M Karras, DPM++ 2M SDE Karras, DPM++ SDE Karras

steps

30 - 45

cfg

6.5 - 9.5

resolution

832x1200, 832x1214, 832x1204, 888x1152, 512x768, 832x1208

vae

SDXL-VAE_0.9.safetensors (63aeecb90f)

other models

FaeTasticSDXL1.6 (7652964f53)

Recommended Hires (High-Resolution) Parameters

upscaler

SwinIR_4x

upscale

denoising strength

0 - 0.45

Tips

The model is merged using SuperMerger in A1111 and LoRAs were trained with Kohya.

Openly discussing model and LoRA creation encourages community learning.

Credit is appreciated for any merges or usage of the model resources.

Model and resources should not be used on third-party sites for monetary gain without permission.

Version Highlights

Spent a lot of time testing and fixing the initial FaeTastic SDXL model....skipped a bunch of iterations and decided on the 6th one for this release. 🥲

Trained a ton of hand LoRAs, I would consider it a bit better now at hands. Obviously, monstrosities can appear still, but can more consistently get good ones.
Trained a brand new Details LoRA that focused on realism and lighting.
FaeTastic Details should be pretty much removed, so you're able to actually use my LoRA with this model now if you prefer more of the cartoon look or just want added colors/details.
The model is way more stable than the first iteration, noticed that some LoRAs were causing artifacts...shouldn't do that anymore.

The only negative I would say is that I feel like it's lost a tiny bit of creativity and kinda lost the unique cartoon faces look. The first model is still available to those who prefer that look. I'm going to keep tweaking this consistently though as I love SDXL and am pretty committed to continuous SDXL resource content.

For my next update I think I'm gonna actually finetune it instead of training LoRAs and merging in. I think this way is probably safer to make sure the model is stable.

Creator Sponsors

For those interested in training SDXL LoRAs, a comprehensive guide by Ally and the author is available: https://civitai.notion.site/SDXL-1-0-Training-Overview-4fb03d5b4cbf482ebe13ffef7bcb8ead

If you have questions or need help with resources or Civitai-related topics, join the Civitai Discord community for assistance!

🥂🎆NEW YEAR EDITION🎆🥂

I needed to reupload the version due to generator issues with uploading the fixed checkpoint that I updated. Same version that has been up for the past few days, so no need to re-download if you have it already. Just added some new pictures for fun.

I've been working on this model for the past couple of weeks and felt like I got it to a point where I'd be happy to release it. I've tried to create a model that has the colors and creativity of 1.5 FaeTastic and also tried to fix some issues that I feel SDXL has. I can't promise that it's perfect, but I feel like it's a step in the right direction.

I've trained several LoRAs that haven't been released for the purpose of merging them into the model, and I'll talk about the model genetics below. Hopefully openly talking about the way I merge and create models/LoRAs will open the door for others to learn as well. :)

Because I believe in the open-source spirit of SD, anyone is free to use this model or any of my LoRAs to merge or use as they see fit in an open-source sense, including selling any images or using them in personal projects. I would be extremely grateful to be credited for any merges or uses of my resources.

However, I am very opposed to having my model and resources I personally train and test and spend hundreds of hours on, be put up on third-party generation sites for their monetary gain where I receive nothing in return.

Model Genetics

Everything was merged with SuperMerger in A1111. All LoRAs were trained with Kohya.

Dreamshaper XL .5 with Rundiffusion XL .5
Added on top of that is the Fae Style SDXL LoRA
FaeTastic V1 SDXL .7 with ProtoVisionXL .3
Added SDXL High Details LoRA
Added SDXL Better Eyes LoRA
Trained a FaeTastic SDXL LoRA on high aesthetic, highly detailed, high resolution 1.5 personal generated images and merged in. This LoRA is pretty awesome, and I'll probably release it on its own as well.
Trained an SDXL LoRA on high-resolution, highly detailed images of realistic, drawn, and digital art of hands. These images were up close pictures of hands as well as images of people holding objects. This was merged in.

Recommended Resources

For those interested in training SDXL LoRAs I highly recommend this guide that Ally and I collaborated on together with a lot of extensive testing and training: https://civitai.notion.site/SDXL-1-0-Training-Overview-4fb03d5b4cbf482ebe13ffef7bcb8ead

If you ever have any questions or need help with my resources or anything Civitai related, I am always happy to assist, you can find me in the Civitai discord! <3