Your current browser has compatibility issues. Please switch toChrome for uninterrupted access.

XL GPT Ghibli | Lâm Panda

951
15
0
1
Illustrious-XL & Animagine-XL Training Anime StyleBoyStyle Boost|Japanese animegptGhibli
Actualizado recientemente: 25/04/01Publicado por primera vez: 25/04/01
Anime Style,Boy,Style Boost,LoRA,SDXLImage info

Want to create a character in the GPT Ghibli Style but for other anime characters? This SDXL version will help you do that.

It saves points/costs compared to the Flux version and can create more than 3 images/day when using ChatGPT :))))))

Instructions for use:

Sampling method: Euler a

Schedule type: Simple

Sampling steps: 30

or

Sampling method: DPM++ 2M SDE

Schedule type: Karras

Sampling steps: 30 - 50 - use 50 if possible

CFG scale: 5 - 7 in which 5 is the best

Upscale:

Hires upscale: 1.25

Hires steps: 20

Hire upscaler: R-ESRGAN 4x+ Anime6B

Denoising strength: 0.15~0.35

Positive Prompt

masterpiece, best quality, high score,

Negative Prompt:

lowres, bad anatomy, bad hands, text, error, missing finger, extra digits, fewer digits, cropped, worst quality, low quality, low score, bad score, average score, signature, watermark, username, blurry

Tag for security level: general, sensitive, nsfw, explicit.

In which, if the platform you are using allows or local, add "nsfw" it will not make your photo too erotic but bring a higher rate of beautiful photos.

Suggestion if you are lazy to write prompt:

Use Grok (it allows longer content and does not limit different types of content):

Command for Grok:

Based on this image (if you have a certain image you want to follow - if not ignore it) help me create 100 similar prompts for SDXL, instructions on how to prompt: quality enhancement, 1girl/1boy/1other, character name, from which series, rating, everything else in any order.

0-0-0-0-0-0-0-0-0-0-0-0

Actually, you will not need the activation keyword for it to work, but you can add it to make Flux understand faster and give better results. ⚡

Note: It works well with FLUX.1-Turbo-Alpha, LORA human face. 👤✨
Useful and FREE resources:

❤️Free server to make art with Flux: Shakker

More FLUX LORA? List and detailed description of each LORA I implement here:  https://maitruclam.com/lora📚

🆕 First time using FLUX? Explanation and tutorial with A1111 forge offline and Comfy UI here: https://maitruclam.com/flux-ai-la-gi/🌐

🛠️ How to train your LORA with Flux? My detailed instructions are here: https://maitruclam.com/training-flux/📚

❤️ Donate me (I would be really surprised if you did that! 😄): https://maitruclam.com/donate

Find me / Contact for work on:

📱 Facebook: @maitruclam4real
💬 Discord: @maitruclam
🌐 Web: maitruclam.com

Expandir todo

Discusión

Más popular
|
Más nuevo
Enviar
No más comentarios
maitruclam
Artista
130
912
156.3k
624
Favorito
Descargar
(193.30MB)
Verificado:2025/03/31
20250331-1743444778280-0010
Detalles
Tipo
LoRA
Recuento de generación en línea
951
Descargas
15
Algoritmo base
SDXL
Descripción de Función
GPT Ghibli Style
Palabras clave
gptgibi
Parámetros Recomendados
Combinación Recomendada de Checkpoint
AnimagineXL v4_v4 OptNEO Anime Cyberpunk hightech| Lâm Panda_XL1.3
Peso recomendado
1
CFG
5
VAE
Ninguno
Licencia
Se puede generar en línea
No se puede fusionar
Licencia ComercialReglas de Uso Comercial
Las imágenes generadas no pueden usarse con fines comerciales
Los modelos no se pueden revender o vender como modelos fusionados
*El alcance de la licencia está establecido por el creador, los usuarios deben utilizar según los requisitos y estándares

Galería

Más popular
|
Más nuevo