XL-v2 Based on Pony Diffusion V6 XLLoRa trained on some gothic style arts.All versions here: <a target="_blank" rel="ugc" href="https://huggingface.co/We11/Goth_girl-v1/tree/main">https://huggingface.co/We11/Goth_girl-v1/tree/main</a>Also, if you want to create high-resolution images, I recommend using "ADetailer" for the good looking faces. Setting i use:for XL-v2: 832x1216 No Hires. Sampling steps: ~25 Sampling method: Euler a CFG Scale: 7Can be used with no other LoRa, but sometimes i use with:<a target="_blank" rel="ugc" href="https://civarchive.com/models/352581/vixons-pony-styles?modelVersionId=398847">gothic neon v1.0 </a>~0.3<a target="_blank" rel="ugc" href="https://civarchive.com/models/315703/gp-somethingweird-style-pony-xl?modelVersionId=354128">[GP] somethingweird style [Pony XL] </a>~0.2<a target="_blank" rel="ugc" href="https://civarchive.com/models/264290/styles-for-pony-diffusion-v6-xl-not-artists-styles?modelVersionId=330475">Concept Art Twilight </a>~0.8And Vae <a target="_blank" rel="ugc" href="https://civarchive.com/models/296576/sdxl-vae">SDXL-VAE</a>for SD1.5: 512x768 or 768x768 or 1024x1024 resolution. Sampling steps: 27 Sampling method: Euler a Upscaler: Latent Upscale by: 1.5 CFG Scale: 5.5SD1.5 v2 trained at 1024x1024 resolution. There are 2 versions that I use to generate, regular v2 and v2S. The regular v2 version is more stable, and v2S is more “Stylish” with more details and the style of the arts on which it was trained on, but less stable especially with faces. So you can try both if you want. Or you can still use v1.5

Gothic Girl

Goth_girl_XL-v2.safetensors

Gothic Girl XL-v2

Goth_girl_XL-v2

Goth_girl-v2.0

Goth_girl-v1.5

Goth_girl-v1.0

From the original Civitai description:XL-v2 Based on Pony Diffusion V6 XLLoRa trained on some gothic style arts.All versions here and it's free: <a target="_blank" rel="ugc noopener noreferrer nofollow" href="https://huggingface.co/We11/Goth_girl-v1/tree/main">https://huggingface.co/We11/Goth_girl-v1/tree/main</a>Also, if you want to create high-resolution images, I recommend using "ADetailer" for the good looking faces.Setting i use:for XL-v2: 832x1216 No Hires. Sampling steps: ~25 Sampling method: Euler a CFG Scale: 7Can be used with no other LoRa, but sometimes i use with:<a target="_blank" rel="ugc noopener noreferrer nofollow" href="https://civitai.com/models/352581/vixons-pony-styles?modelVersionId=398847">gothic neon v1.0 </a>~0.3<a target="_blank" rel="ugc noopener noreferrer nofollow" href="https://civitai.com/models/315703/gp-somethingweird-style-pony-xl?modelVersionId=354128">[GP] somethingweird style [Pony XL] </a>~0.2<a target="_blank" rel="ugc noopener noreferrer nofollow" href="https://civitai.com/models/264290/styles-for-pony-diffusion-v6-xl-not-artists-styles?modelVersionId=330475">Concept Art Twilight </a>~0.8And Vae <a target="_blank" rel="ugc noopener noreferrer nofollow" href="https://civitai.com/models/296576/sdxl-vae">SDXL-VAE</a>Triggers: goth girl, goth girl 1girlGo give the creator some love if you can!

XL-v2 Based on Pony Diffusion V6 XL

LoRa trained on some gothic style arts.

All versions here and it's free: https://huggingface.co/We11/Goth_girl-v1/tree/main

Also, if you want to create high-resolution images, I recommend using "ADetailer" for the good looking faces.


Setting i use:

for XL-v2: 832x1216 No Hires. Sampling steps: ~25 Sampling method: Euler a CFG Scale: 7

xl-v2

XL-v2 Based on Pony Diffusion V6 XLLoRa trained on some gothic style arts.All versions here: <a target="_blank" rel="ugc" href="https://huggingface.co/We11/Goth_girl-v1/tree/main">https://huggingface.co/We11/Goth_girl-v1/tree/main</a>Also, if you want to create high-resolution images, I recommend using "ADetailer" for the good looking faces. Setting i use:for XL-v2: 832x1216 No Hires. Sampling steps: ~25 Sampling method: Euler a CFG Scale: 7Can be used with no other LoRa, but sometimes i use with:<a target="_blank" rel="ugc" href="https://civitai.com/models/352581/vixons-pony-styles?modelVersionId=398847">gothic neon v1.0 </a>~0.3<a target="_blank" rel="ugc" href="https://civitai.com/models/315703/gp-somethingweird-style-pony-xl?modelVersionId=354128">[GP] somethingweird style [Pony XL] </a>~0.2<a target="_blank" rel="ugc" href="https://civitai.com/models/264290/styles-for-pony-diffusion-v6-xl-not-artists-styles?modelVersionId=330475">Concept Art Twilight </a>~0.8And Vae <a target="_blank" rel="ugc" href="https://civitai.com/models/296576/sdxl-vae">SDXL-VAE</a>for SD1.5: 512x768 or 768x768 or 1024x1024 resolution. Sampling steps: 27 Sampling method: Euler a Upscaler: Latent Upscale by: 1.5 CFG Scale: 5.5SD1.5 v2 trained at 1024x1024 resolution. There are 2 versions that I use to generate, regular v2 and v2S. The regular v2 version is more stable, and v2S is more “Stylish” with more details and the style of the arts on which it was trained on, but less stable especially with faces. So you can try both if you want. Or you can still use v1.5

Files with SHA256: a0a604c260b115364208c465b7c06ec7375dfb4fdf405e960850dc203e7a3d62