models/Fantasy Flux & XL (digital painting style) by nymical - fantasy-flux-v1.0

Fantasy Flux & XL (digital painting style) by nymical - fantasy-flux-v1.0

10/23/2025

5:54:06 PM

Related Keywords & Tags

cosplay,digital painting,digital painting style,fantasy,fantasy-flux-v1.0,fantasy flux & xl (digital painting style) by nymical,fantasy generations,flux.1 d,fp8 t5xxl,kohya-ss training,lora,midjourney,nymical,painting,style,version v2,version v3.0

Anime-style portrait of an elven woman with long golden hair, blue eyes, and ornate silver armor glowing in warm golden light.

A detailed dark fantasy oil painting of a monstrous ladybug with oversized features and a menacing expression, featuring a vibrant red shell and sharp black limbs against a minimal neutral background.

Close-up of a young woman holding a half-broken white porcelain Kitsune mask with red swirling accents covering one side of her face, selective color highlights the mask's red details against a black and white portrait.

Recommended Parameters

samplers

Euler

steps

cfg

Tips

Sample images are generated with strength 1 but users can experiment with different strengths.

If generating locally, use the fp8 version of t5xxl for better compliance with prompt details, especially for hair or skin color.

The model was trained 10 different times with 3 epochs each to achieve acceptable results.

Version Highlights

This is the first version.

If you use this model, please post at least one image directly here on this model page!!

This Lora is intended to create digital painting style fantasy generations.

The sample images are generated with strength 1, but experiment as you like. The workflow is available in the sample images in v1.

The v2 makes the images sharper and clearer, and a bit more realistic.

The version, v3.0 makes gens more realistic but still more fantastical.

The training was done in kohya-ss with the default flux settings. This is my first model published here, so I don't know much, but please try it and review it. Any donations are welcome as I had to train 10 different times with 3 epochs each to get something acceptable.

(All the images provided are generated with fp8 version of t5xxl, the fp16 version doesn't follow prompt very well (even without any lora), so I don't know what's going on with that. If you're generating locally, try the fp8 version of t5xxl if flux ignores your specific hair or skin color instructions.)