modelli/Not Artists Styles for Pony Diffusion V6 XL - Concept Art DarkSide [M]

Not Artists Styles for Pony Diffusion V6 XL - Concept Art DarkSide [M]

10/17/2025

9:44:40 AM

Parole Chiave e Tag Correlati

anime,bara,concept art darkside [m],arte digitale,femmina,lora,maschio,not artists styles for pony diffusion v6 xl,obuyb404,pony,ponyxl,style,arte occidentale,yaoi

A close-up of a cute, small green frog surrounded by vibrant pink flowers with dramatic light highlighting its textured skin and large eyes.

Side view of a special forces soldier with a blonde ponytail blowing pink bubblegum, wearing a black tactical uniform with scars on her face, against a foggy, red glowing ember background.

Close-up of a blindfolded woman with pale skin wearing a white robe decorated with gold and a gold-decorated veil, standing inside a church with stained glass windows in the background.

Portrait of a female drider character with dark skin, white hair tied in a ponytail, wearing elegant gold jewelry and a white top

Portrait of a female drider character with dark skin, striking blue eyes, white hair in a ponytail, and gold jewelry including earrings and forehead ornament.

A tall black shadow entity with blue glowing eyes, surrounded by deep shadows in an abandoned basement with haunting tendrils.

Realistic concept art of a goth girl with long black hair wearing a white crop top, black pants, and cross jewelry, posed with one arm behind her head.

Young woman with short dark hair in a futuristic workshop, wearing an orange jacket and yellow goggles, with a confident expression.

An AI generated image using Stable Diffusion depicting a female sorceress with long black hair, dressed in fantasy attire, holding a ball of fire in her hand against a cloudy, dark background.

A female warrior dressed in intricate fantasy armor in an alleyway, generated using Stable Diffusion.

A detailed mech robot in futuristic battle armor, created with Stable Diffusion AI.

Prompt Consigliati

score_9, score_8_up, score_7_up, rating_safe, concept art, realistic, dark theme, low light, solo, long hair, looking at viewer, standing, outdoors

Prompt Negativi Consigliati

score_6_up, score_5_up, score_4_up, text, watermark, low-quality, signature, moiré pattern, downsampling, aliasing, distorted, blurry, glossy, blur, jpeg artifacts, compression artifacts, poorly drawn, low-resolution, bad, distortion, twisted, excessive, exaggerated pose, exaggerated limbs, grainy, symmetrical, duplicate, error, pattern, beginner, pixelated, fake, hyper, glitch, overexposed, high-contrast, bad-contrast

Parametri Consigliati

samplers

DPM++ 2M SDE Karras

steps

cfg

resolution

768x1152

vae

sd_xl_0.9.vae.pt

other models

Concept Art DarkSide Style LoRA_Pony XL v6 (8f1dcea2af05), ponyDiffusionV6XL_v6 (67ab2fd8ec)

Suggerimenti

Styles are trained on synthetic data and do not copy the styles of artists

Photo 2 is trained on real data (Dataset from Unsplash)

Recommended LoRA Strength (Weight): 0.8-1

Preview generated without using ADetailer & Hires. fix

Punti Salienti della Versione

Concept Art DarkSide is a merge of 3 models

0.30 - Concept Art Dark

0.35 - Concept Art Night (Unpublished)

0.35 - Concept Art Night Not Edited (Unpublished)

Recommended LoRA Strength: 0.7-1

For one reason or another, I don't publish some styles. I don't always manage to create a good style the first time, sometimes I have to merge several models to get the style I want.

kohya_ss does not allow to merge models with different Network Dimension (Rank). That's why I don't change the LoRA training settings.

Styles are trained on synthetic data and do not copy the styles of artists!

Photo 2 - is trained on real data (Dataset from Unsplash)

[M] Merged LoRAs

Recommended LoRA Strength (Weight): 0.8-1

Preview generated without using ADetailer & Hires. fix

Contributore

obuyb404

Just a guy who is interested in Neural Networks, mainly Stable Diffusion. I create Styles and LoRA characters that I like, mostly I create male characters.

Eon 2.5D - v2.0

Dark Fantasy 90's anime style illustriousXL - V1

Usa questo modello