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

True-IP design

3.8k
83
162
29
Uso comercialCartoon styleIP CharacterObject Enhance|IP Design
Actualizado recientemente: 25/04/13Publicado por primera vez: 23/10/24
Cartoon style,IP Character,Object Enhance,LoRA,FLUX.1Image info
Cartoon style,IP Character,Object Enhance,LoRA,FLUX.1Image info
Cartoon style,IP Character,Object Enhance,LoRA,FLUX.1Image info
Cartoon style,IP Character,Object Enhance,LoRA,FLUX.1Image info
Cartoon style,IP Character,Object Enhance,LoRA,FLUX.1Image info
Cartoon style,IP Character,Object Enhance,LoRA,FLUX.1Image info
Cartoon style,IP Character,Object Enhance,LoRA,FLUX.1Image info
Cartoon style,IP Character,Object Enhance,LoRA,FLUX.1Image info

Standard IP design view


Thanks to the expressiveness of FLUX, the real-IP design has ushered in a major upgrade, and the overall texture and expressiveness have been greatly improved. Moreover, they are all very standard front, side and back three views. FLUX requires you to have very accurate writing of the prompt words, as follows


* Resolution: 1536 width x 1024 height for best results


LoRA weight recommendation: around 0.8


Trigger word: Three views, including front, side and back


Prompt word template:


This image is a digital rendering of the [subject], from three angles: front, side and back. This character has a [specific image description of the subject]. The background is pure white, emphasizing the character.


For example:


This image is a digital rendering of a yellow cartoon tiger with black stripes and a white nose, taken from three angles: front, side and back. The tiger has a pair of big, round black eyes, a pair of small black ears and a black tail. It is chubby and cute, with three black stripes on its arms and legs. The background is pure white, highlighting the image of the tiger.


Tips: You can optimize the prompt words according to your needs, or refer to the prompt words in the example picture. Just write the picture you want in natural language. It is recommended to use Chatgpt to assist writing. The FLUX model needs detailed and accurate prompt words to maximize its capabilities. I recommend using a standard reference picture and sending it to ChatGPT to obtain accurate description words, and then processing prompt words on this basis


Use natural language, and provide the theme and format for Deepseek to polish and write


Keep the rest as default, as follows


Negative prompt words: Not required


Base model: X潮玩_FLUX版


Sampling method: Euler


CFG: 3.5


Iteration steps: 30 Too low may cause image blur


ComfyUI workflow recommendation:


https://www.liblib.art/modelinfo/5171f6fa89304df5b45e87e3118ec3b3


Model use statement:


1. Without authorization, you may not host this model and its derivative versions on other service platforms or integrate them into applications and websites.


2. You may not use this model to create and disseminate illegal or harmful content. Please comply with relevant laws and regulations and public order and good customs.


3. You shall use the content generated by this model after independent judgment. Any intellectual property issues and legal risks that may arise from this shall be borne by you. I am not responsible for any losses caused by this.


4. If you want to use the work for commercial purposes, you need to make enough manual modifications to the work so that it can be judged as your personal work.

Expandir todo
Traducir al español

Discusión1

Más popular
|
Más nuevo
Enviar
avatar
wuxiaoqiu
nasterpiece,best quality,character design,three views,front view,side view,back. view,chibi,cute,simple background
2024/08/15 10:28:14
0Responder
No más comentarios
Hongke
Artista
420
1.4k
204.0k
3.1k
Favorito
Descargar
(584.36MB)
Verificado:2024/11/30
v3.0
ExclusivoDetalles
Tipo
LoRA
Recuento de generación en línea
118
Descargas
2
Algoritmo base
FLUX.1
Descripción de Función
IP设计标准三视图
Parámetros Recomendados
Combinación Recomendada de Checkpoint
Better FLUX_Compatible with various LoRA_兼容各种LoRA_V1
Peso recomendado
0.8
CFG
3.5
VAE
Ninguno
Algoritmo de Escalado en Alta Resolución
R-ESRGAN_4x+ Anime6B
Licencia
Se puede generar en línea
No se puede fusionar
Licencia ComercialReglas de Uso Comercial
Las imágenes generadas se pueden usar para fines comerciales (solo para miembros)Actualizar ahora >>
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

Galería162

Más popular
|
Más nuevo
Pinned
avatar
Hongke
Image info
Image info
Image info
avatar
양희석
Image info
avatar
ernest fu
Image info
Pinned
Image info
avatar
sanscouer
Image info
Image info
Image info
avatar
Beibang
Image info
Pinned
Image info
Image info
Image info
avatar
Hongke
Image info
avatar
Hongke
Image info
Pinned
avatar
D. Olivera
Image info
Image info
avatar
p334557.
Image info
avatar
Beibang
Image info
avatar
Hongke
Image info