Diffus
Commencer
modèles/🥂🎆SDXL FaeTastic🎆🥂 - v1.6

🥂🎆SDXL FaeTastic🎆🥂 - v1.6

Faeia
|
8/19/2025
|
3:35:34 AM
| Discussion|
0
Hyper detailed digital art of a jukebox with a circular turquoise-blue center, surrounded by intricate mechanical switches, user interface labels, and volumetric rim lighting.
A hyper-detailed dark fantasy digital artwork featuring towering Underworld Towers surrounded by marsh mists, backlit with volumetric and rim lighting effects.
A detailed cyberpunk-style hovering vehicle with a large glowing clock face, surrounded by neon blue fiber optic lights in a futuristic repair garage.
A hyper detailed celestial spiked wheel made of steel with glowing fluorescent and rope lights, set against a starlit dusk sky with mountains and fantastical spires.
Highly detailed digital art of a spiked quantum force field nexus with vibrant blue energy core, surrounded by red roses inside a futuristic obsidian stone chamber.
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.

Paramètres recommandés

samplers

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

steps

30 - 45

cfg

6.5 - 9.5

resolution

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

vae

SDXL-VAE_0.9.safetensors (63aeecb90f)

other models

FaeTasticSDXL1.6 (7652964f53)

Paramètres haute résolution recommandés

upscaler

SwinIR_4x

upscale

2

denoising strength

0 - 0.45

Conseils

Model merging done with SuperMerger in A1111.

All LoRAs were trained using Kohya.

Model and LoRAs are open-source and free to use including commercial use, but author requests credit for merges or use.

Author opposes third-party generation sites profiting from their model without compensation.

For training SDXL LoRAs, refer to the collaborative guide: https://civitai.notion.site/SDXL-1-0-Training-Overview-4fb03d5b4cbf482ebe13ffef7bcb8ead.

Author offers support in Civitai Discord for resource-related questions.

Points forts de la version

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.

Sponsors du créateur

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

🥂🎆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.

  1. Dreamshaper XL .5 with Rundiffusion XL .5

  2. Added on top of that is the Fae Style SDXL LoRA

  3. FaeTastic V1 SDXL .7 with ProtoVisionXL .3

  4. Added SDXL High Details LoRA

  5. Added SDXL Better Eyes LoRA

  6. 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.

  7. 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

Précédent
AlbedoBase XL - v3.1-Large
Suivant
Midjourney V6.1 meets FLUX 🖼️ [+ILLUSTRIOUS / SDXL] - FLUX v0.1
Utiliser ce modèle

Détails du modèle

Type de modèle

Checkpoint

Modèle de base

SDXL 1.0

Version du modèle

v1.6

Hash du modèle

7762ec03a3

Créateur

Faeia's avatar
Faeia

Discussion

Veuillez vous log in pour laisser un commentaire.

Images par 🥂🎆SDXL FaeTastic🎆🥂 - v1.6

Hyper detailed digital art of a jukebox with a circular turquoise-blue center, surrounded by intricate mechanical switches, user interface labels, and volumetric rim lighting.
A hyper-detailed dark fantasy digital artwork featuring towering Underworld Towers surrounded by marsh mists, backlit with volumetric and rim lighting effects.
A detailed cyberpunk-style hovering vehicle with a large glowing clock face, surrounded by neon blue fiber optic lights in a futuristic repair garage.
A hyper detailed celestial spiked wheel made of steel with glowing fluorescent and rope lights, set against a starlit dusk sky with mountains and fantastical spires.
Highly detailed digital art of a spiked quantum force field nexus with vibrant blue energy core, surrounded by red roses inside a futuristic obsidian stone chamber.
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.

Images avec modèle de base

Photorealistic scene of undead characters including zombies and skeletons walking through a spooky Halloween cemetery filled with glowing jack-o'-lantern pumpkins and desiccated trees in a dark, foggy atmosphere.

Images avec cartoon

A cute little owlbear cub sitting on grassy ground surrounded by flowers in a forest, featuring a large beak and big expressive eyes.
A detailed digital artwork of a Persian girl with flowing red hair, wearing ornate gold jewelry and blue and white linen clothing, set in a cinematic fantasy atmosphere.
Cartoon style illustration of a science kid with a surprised face reading a book, surrounded by pyramids, planets, dinosaurs, and colorful cosmic elements.
Two panel comic titled 'Civitai's Rating System' featuring a cute penguin happily working on a laptop in the first panel and a shocked blue robot labeled 'CIVITA!' at a computer in the second panel.
Two girls from Neon Genesis Evangelion, Souryuu Asuka Langley in green and orange plugsuit and Ayanami Rei in white plugsuit, posed under a starry night sky with a glowing moon.
Profile of a blue-skinned alien woman wearing a detailed red suit with golden collar and a red tiara, illustrated in a low saturation cartoon style.
Silhouette of a cartoon girl with pigtails holding a dripping knife against a bold red background.
A cartoon-style pot character with a human-like face featuring orange eyes and cracked skin, standing in a cracked, rocky lava landscape with mountains in the background.

Images avec fantasy

A white-haired girl with bright blue eyes stands smiling in a flowery meadow under a moonlit night sky, surrounded by flying petals and illuminated by cinematic lighting.
Glowing golden One Ring resting on a detailed Middle-earth map with cinematic dramatic lighting and shadows.
A girl riding on a giant orange goldfish surrounded by smaller goldfish and water bubbles in a bright blue sky
Hyper realistic oil painting of a punk rock girl with pink hair, wearing a Mad Max style black leather jacket and cables on her body, standing in an urban street setting.
A determined female knight with red hair in a high ponytail wearing black armor stands in a sunlit grassland holding a sword and shield with a fantasy castle in the background under a blue sky.
A grand fantasy castle with numerous towers and a tall wizard tower, situated on a floating island surrounded by a lake, connected by a stone bridge under a bright blue sky with clouds.
An anime girl with blonde hair and a white dress walks through a dark forest illuminated by numerous glowing orange jellyfish drifting around her.
A white dragonborn child sitting on a pile of gold coins, wearing detailed armor with horns and claws, illuminated by warm sunlight.
A massive land whale monster covered in moss with sharp teeth and glowing eyes confronts a lone cloaked figure in a misty magical green forest, rendered in fantasy style.
Portrait of a girl with bright blue eyes and short dark-blue and purple hair adorned with pink Lisianthus flowers, painted in a dreamy watercolor style emphasizing light pink and light azure tones.

Images avec highly detailed

A beautifully detailed anime-style rendition of a wooden Japanese house surrounded by vibrant red and pink trees, with a serene blue river and wooden bridges under a bright blue sky.
Glowing golden One Ring resting on a detailed Middle-earth map with cinematic dramatic lighting and shadows.
Portrait of a handsome young man with dark hair in a patterned Hawaiian shirt standing beside a blonde girl in a white angel costume dress, with neon-lit ferris wheel and party at Santa Monica in the background during evening.
Highly detailed upper body portrait of Asuka Langley wearing a shiny red Evangelion suit with long red hair under dramatic spotlight and dark lighting.
A futuristic sci-fi spacescape depicting the Ceres colony with towering sleek structures emitting bright vertical beams of light under a dark starry sky and a visible planet in the background.
Dark blue-skinned woman named Ranni wearing a large pointed wizard hat with intricate details, multiple arms folded and hands together, with glowing blue eyes under a starry night sky.
A fat, muscular dwarf with long grey hair and beard leaning against a wooden bar in a tavern, holding a tankard of beer with moody lighting and tattoos.
Split screen close-up portrait of two male cyborgs, Raiden with silver hair and Jetstream Sam with dark hair and beard, showcasing detailed mechanical elements.
Young woman dressed in a cowgirl outfit with a brown hat and red scarf riding a dark brown horse outdoors near wooden structures under a clear sky.
Warrior with flowing white hair in detailed Nordic armor standing near a steep cliff by an epic fjord landscape