models/Surrealidescent - v1

Surrealidescent - v1

8/16/2025

11:06:57 PM

Related Keywords & Tags

aesthetic,cats,flux.1 d,fruit,ice cubes,iridescent,iridescent style,lora,markury,photorealim,photorealism,sparkly food,style,surreal photo,surreal photography,surrealidescent,surrealism,v1

A surreal tree made entirely of shimmering glass with iridescent green and pink foliage, its branches extending into a bright blue sky filled with fluffy white clouds.

Surreal iridescent octopus with sparkling tentacles floating gracefully through a glowing galaxy filled with stars and nebula-like orbs.

A fantasy elf warrior woman with long flowing blonde hair and pointed ears, dressed in highly detailed ceremonial metal armor, gripping an ornate sword, set against a misty, ethereal forest background.

A young female cyborg with long hair and synthetic limbs stands in a misty futuristic cityscape with neon lights and tall buildings.

Anime-style female warrior holding a katana sword, wearing sheer white top and high-gloss black shorts under pink and blue neon lighting.

Close-up of a woman wearing an intricate, crystal headpiece with sharp, angular shapes, illuminated by blue lighting in a studio setting.

Recommended Negative Prompts

(not used)

Recommended Parameters

samplers

euler_beta

steps

cfg

resolution

832x1216

Tips

Mix this LoRA with another for enhanced skin detail effects

Version Highlights

Trained with SimpleTuner on 1x RTX4090

Training steps: 4500
Learning rate: 2e-05
Effective batch size: 2
Optimizer: optimi-lion
Quantised: Yes: int8-quanto
LoRA Rank: 16
LoRA Dropout: 0.1

This is a pretty simple LoRA trained on my pinterest homepage. It's full of those renders of ice cubes and fruit, sparkly food, and cats doing weird stuff.

It's also full of surreal photography, which is hard to categorize as strictly a style when it's quite dependent on the content and context, but you know it when you see it.

It's a big ol' mix and I think of it as like that personalize flag on Midjourney. It generally skews generations toward photorealism with shorter prompts than usual (as opposed either writing verbose prompts for photorealistic detail or using a short prompt and getting that smooth synthetic look Flux is known for). With that being said, it doesn't actually add things like skin details since that wasn't the focus of the dataset, so you may want to mix it with another LoRA for that.