modèles/Velvet's Mythic Fantasy Styles | Flux + Pony + illustrious - Pony Portrait Style

Velvet's Mythic Fantasy Styles | Flux + Pony + illustrious - Pony Portrait Style

VelvetS

10/22/2025

11:48:11 PM

| Discussion|

Mots-clés et tags associés

A tall elegant woman with obsidian black skin and long white hair wearing a torn white hooded desert robe, standing in a sunny desert with sandstone cliffs and blue sky.

Realistic portrait of an underwater explorer with short wavy blue hair, wearing an advanced diving suit with bioluminescent accents and goggles, standing amidst ancient ruins with cinematic lighting.

A slender succubus with short red horns, large burning wings, and fiery hair, wearing a revealing red and gold dress, standing amidst flames with molten lava hands.

Prompts recommandés

monochrome,greyscale,MythAn1m3,MythP0rt

(score_9, score_8_up), score_7_up, zPDXL, <lora:MythP0rtr4itStyle:1>, solo, 1girl, mythp0rt

Prompts négatifs recommandés

score_6, score_5, score_4, zPDXL-neg, negativeXL_D, blurry, worst quality, low quality, bad anatomy, bad hands, missing fingers, fewer digits, source_furry, ugly

Paramètres recommandés

samplers

DPM++ 2M Karras, Euler a

steps

28 - 30

cfg

clip skip

resolution

832x1216

vae

sdxl.vae.safetensors

other models

MythP0rtr4itStyle (741494ca3d7c), ponyDiffusionV6XL_v6StartWithThisOne (67ab2fd8ec)

Paramètres haute résolution recommandés

upscaler

4x_NMKD-Siax_200k, 4x_NMKD-Superscale-SP_178000_G

upscale

1.5

steps

denoising strength

0.4

Conseils

For Manga Style, including 'monochrome' or 'greyscale' in your prompt can greatly enhance results.

Use weight ranges 0.6-1 for Manga, Anime Illustrations, and Portrait styles; 0.5-1.5 for Flux style, with 1 recommended.

Change Diffusion settings in SD Forge NF4 to 'Automatic (fp16 LoRA)' when using this LoRA.

Copy generation data from examples or contact the author if you encounter issues.

Points forts de la version

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.

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