WAI-illustrious-SDXL - GGUF Ultimate Edition 🏭
Este repositorio ofrece la colección en formato GGUF del modelo original WAI-illustrious-SDXL. Optimizados para inferencia con poca memoria.
� Tabla de Comparativa de Cuantizaciones
| Versión | Tipo | Peso | Calidad | Uso Recomendado |
|---|---|---|---|---|
| Q4_K_M | Medium | ~5-7GB | Basica | Balance / Velocidad |
| Q5_K_M | Large | ~8-10GB | Alta | Calidad |
| Q8_0 | Ultra | Original | Alta | Calidad |
⚙️ Guía de Optimización y Comparativa de Parámetros
Para obtener los mejores resultados con esta versión GGUF, se recomiendan los siguientes ajustes:
1. 🎚️ Comparativa de CFG (Classifier Free Guidance)
| CFG Scale | Efecto en GGUF | Resultado Visual |
|---|---|---|
| 1.0 - 3.5 | Suave / Realista | Menos contraste, ideal para estilos fotográficos. |
| 4.0 - 6.5 | Recomendado | Balance perfecto entre fidelidad al prompt y detalle. |
| 7.0 - 9.0 | Estilizado | Colores más saturados y bordes más definidos. |
2. ⚡ Comparativa de Pasos (Sampling Steps)
| Pasos | Rendimiento | Nivel de Detalle |
|---|---|---|
| 15 - 20 | Ultra Rápido | Bocetos rápidos o previsualizaciones. |
| 25 - 35 | Óptimo | El equilibio para GGUF con casi cero ruido. |
| 40+ | Estándar | Máximo refinamiento de texturas complejas. |
3. 🌫️ Comparativa de Denoise (Solo para i2i / Hires Fix)
- 0.35 - 0.45: Mantiene la estructura original pero con limpieza de artefactos.
- 0.50 - 0.65: El rango ideal para añadir detalle sin deformar el sujeto.
- 0.70+: Cambio significativo de composición (usar con precaución).
👤 Créditos y Atribución
- Autor Original: WAI0731
- Cuantización Experta: void-gryph
🚀 Despliegue en ComfyUI
- Archivo GGUF: Mover a
ComfyUI/models/unet/ - Nodos Requeridos: Es necesario tener instalado ComfyUI-GGUF.
- Componentes Originales: Use el CLIP y VAE incluidos en este repo para máxima fidelidad (extraídos sin prefijos de contenedor).
📝 Nota del Autor Original
If you want to use more my checkpoint online generation, please visit here.
https://tensor.art/u/762555264535746522
WAI-NSFW-illustrious-SDXL - SeaArt AI Model
WAI_NSFW-illustrious-SDXL_NSFW-illustrious-SDXL_NSFW-illustrious-SDXL_NSFW-illustrious-SDXL-Checkpoint-WAI-Shakker
Character Select SAAThis is a Stand Alone App with AI prompt, Semi-auto Tag Complete and ComfyUI/WebUI API support.
Now supports 5058 (includes multiple costumes) Character list.
https://github.com/mirabarukaso/character_select_stand_alone_app
One-Click embedded package In case you don't know how to build your own Python enverment, try the embeded_env_for_SAA Down and unzip to your computer Db-click #run_XX.bat
https://huggingface.co/datasets/flagrantia/character_select_stand_alone_app/resolve/main/embeded_env_for_SAA.zip 下载解压到任意目录,运行 #run_CN Download and extract to any directory. Run #run_CN or #run_EN
Online Quick search characterCharacter Select Saa - a Hugging Face Space by flagrantia
Please do not add too many quality and aesthetic-related tags, nor overly long negative prompts, as this will actually reduce image quality and make it more blurry.
v16
Adjusted the model’s overall default style, enhancing visual cleanliness and improving character accuracy.
Recommended settings:Steps: 15-30
CFG scale: 5-7
Sampler: Euler a
The VAE is already integrated, please do not ask such questions anymore.
use size larger than1024x1024 for the original dimensions.
Hires upscale: 1.5, Hires steps: 20, Hires upscaler: R-ESRGAN 4x+ Anime6B,Denoising strength: 0.35~0.5
There are four safety rating tags: general, sensitive, nsfw,explicit. Users are expected to consciously add "nsfw" to negative prompts to filter inappropriate content.
Positive Prompt
,masterpiece,best quality,amazing quality,
Negative Prompt
bad quality,worst quality,worst detail,sketch,censor,
V5-V15 User ManualV1-V4 are outdated,please do not download them anymore.
This is a list of characters that have been tested and are implementable on V11.
sieecc/WAI-NSFW-illustrious-SDXL at main
These are just temporary and not all tests have been completed yet; more will be added subsequently.
Recommended settings:Steps: 25-40
CFG scale: 5-7
Sampler: Euler a
The VAE is already integrated, please do not ask such questions anymore.
use size larger than1024x1024 for the original dimensions.
Hires upscale: 1.5, Hires steps: 20, Hires upscaler: R-ESRGAN 4x+ Anime6B,Denoising strength: 0.35~0.5
There are four safety rating tags: general, sensitive, nsfw,explicit. Users are expected to consciously add "nsfw" to negative prompts to filter inappropriate content.
Positive Prompt
masterpiece,best quality,amazing quality,
Negative Prompt
bad quality,worst quality,worst detail,sketch,censor,
GGUF Quantizer - Comprimiendo la inteligencia artificial, píxel a píxel.
- Downloads last month
- 244
4-bit
5-bit
8-bit