models/Velvet's Mythic Fantasy Styles | Flux + Pony + illustrious - Flux Sharp Lines

Velvet's Mythic Fantasy Styles | Flux + Pony + illustrious - Flux Sharp Lines

|
4/2/2026
|
5:14:34 AM
| Discussion
Side view of a blonde woman kneeling indoors wearing a floral kimono and thigh-high boots, holding a katana in a rustic wooden room.
Side view of a cybernetic woman with long black hair wearing a red cropped hoodie, seated on a dark industrial stool showing her mechanical legs and arms under moody lighting.
A dark, mystical fantasy character crouching on a snow-covered ledge in an urban, industrial setting. She has long dark green hair, large curved horns, pointed ears, and wears gothic armor and a fur cloak.
A pale woman with intense red glowing eyes wears a detailed dark gray fedora hat with skull decoration, a red collared shirt with black lace, and an ornate dark jacket, holding a cigarette against a deep red background.
A regal fire empress in molten lava gown stands in a volcanic wasteland as a magnificent fiery phoenix soars behind her with blazing wings.

Recommended Prompts

SharpL1nes

Recommended Parameters

samplers

DPM++ 2M

steps

30

cfg

1

resolution

832x1216

other models

FluxMythSharpL1nes (2dc611cd9da9), flux1-dev-bnb-nf4-v2 (bea01d51bd)

Tips

For the Manga Style (Blood Moon), using "monochrome" or "greyscale" in your prompt substantially boosts the results.

Use weight ranges 0.6-1 for Manga, Anime Illustrations, and Portrait Styles to get optimal effects.

Flux Style works best with weight around 1, usable from 0.5 to 1.5; experiment within this range to find the best results.

For SD Forge using NF4 model, set Diffusion in Low Bits from Automatic to Automatic (fp16 LoRA) for compatibility.

If issues arise, copy generation data from provided examples or contact the author via direct message.

Update Flux Version

The new version has been trained to work on Flux models. From my testing Flux is amazing with sentence like prompts, and turns booru prompts to anime pics that don't have a lot of details but this LoRA fixes that:

I tested it on SD Forge using the NF4 model and it work fine, you just need to change the Diffusion in Low Bits from Automatic to Automatic (fp16 LoRA) like this:

The rest of the LoRAs are designed to work with Pony Diffusion XL, or any other Pony model.

How to use

1- Manga Style (Blood Moon): Made from high quality monochrome images to give you a manga feel, oh and I called it blood moon because if you have something red in your prompt you might get a cool effect xD.

  • Trigger words: This LoRA is without Trigger Words, but having "monochrome, greyscale" in your prompt can greatly enhance the results.

  • Works on: 0.6-1 weights

2- Anime Illustrations Style: Made from very colorful and high quality data to improve your images and give them a badass feel.

  • Trigger words: MythAn1m3

  • Works on: 0.6-1 weights.

3- Portrait Style: This style is made to create high quality portraits of fantasy characters, and most of the training data is made with semi realistic art style.

  • Trigger words: MythP0rt

  • Works on: 0.6-1 weights.

4- Flux: This style is made to create high quality fantasy art, and it has training data similar to the Portrait Style

  • Trigger words: MythP0rt

  • Works on: 0.5-1.5 weights, feel free to experiment but I recommend you to put the weight at 1.

Other styles coming soon.

If you have any problem try copying generation data from my examples, or send me a DM

I can't wait to see what other people make with this :)

Contributor

Previous
New Incase Style (2024) | NoobAI | Illustrious | PonyXL | Flux.1 D - ILLUSTRIOUS NOOBAI
No next image

Model Details

Model type

LORA

Base model

Flux.1 D

Model version

Flux Sharp Lines

Model hash

6249169cf8

Trained words

SharpL1nes

Creator

Discussion

Please log in to leave a comment.