Model
Trends
.ai
Model
Trends
.ai
los mejores modelos de IA de código abierto
Ejecutar en local
modernDisneyXL_v3.safetensors
6.46 GB · SafeTensor · bf16 · full
Las descargas las sirve Civitai. Algunos creadores piden iniciar sesión en Civitai primero.
AD
<modern-disney3-xl>
Sobre este modelo
STABLE DIFFUSION XL 1.0 · Modelos base
Creado por
massOxygen
en Civitai
Notas del creador
I added an inpainting version for this model, I recommend using the "color correction" option under the img2img tab in AUTO1111 settings. To do this "drop-in replacement" inpainting shown in the image, you need to set "Masked content" to "latent noise", and set "Denoising strength" to 1. I used Mask blur 16 and padding 8. Put "error" in negative prompt to suppress artifacts. Version 3: I think this one is a major improvement to v2, I used the same prompts in the image showcase as a comparison. The trigger tokens are in the model description to the right, they are not necessary but recommended for most cases. Try adding "pixar render" if you want more disney/pixar style images. The now ancient "modern disney v1" model was one of my favorite, so I decided to carry on some of its legacy by training an SDXL version! Img2img aka "Disneyfication": - Choose any image you want (realistic photos probably work best) - Resize your image so that its resolution fits within SDXL resolution bounds (e.g. resize to 1024px on the shorter side) - Use AUTO1111 img2img tab and load image (or the equivalent for any alternative UI) - Choose Euler sampler (usually best results), start with denoising 0.1, steps 40-120 (lower denoising needs higher steps to compensate) - Enter "modisn disney style" as a prompt (sometimes giving a general description of the image can help, e.g. "modisn disney style, girl holding a cat"). You can try working with the negative prompt but keep both prompts short - Hit generate and see what you get! Play around with the settings, higher denoising values allow for stronger Disney render effect but will also deviate more strongly from the original image. CFG also controls the strength of the effect. - (Optional) Choose AUTO1111 loopback script on the bottom, I recommend staying with only 2 loops, start with the first loop at 0.1 and the second at 0.15 or 0.2, and see what you can do from there. It will allow you to use higher denoising values while suppressing unwanted "mutations" in the image.
Palabras de activación
modisn disney
modisn disney style
6,571 descargas · 370 me gusta en Civitai
SHA256
248C0781906BEE299C820F20463FE586AE6F92BAC6D2C6E085C38B2DAE881AD9
ID de modelo de ModelTrends.ai
#2682
Denunciar contenido
Renders de ejemplo
Prompts y ajustes compartidos por quienes hicieron estos renders en Civitai. Elige un render para ver cómo se hizo.
Ajustes
Sampler
LCM
Pasos
13
Guidance
2
Semilla
1018483065230922
Tamaño
768x1344
Prompt
attractive beautiful female woman, wearing tight christmas outfit, ugly christmas sweater, outside tavern, night time snowy snowing, cozy warm window, (4k, 8k, extreme detail, ultra quality, HD, high definition, HDR, high dynamic range, octane render, Masterpiece, best quality, colorful, volumetric lighting, ultra definition, disney 3d pixar style)
Ajustes
Sampler
LCM
Pasos
13
Guidance
2
Semilla
999118613560825
Tamaño
768x1344
Prompt
(devil american soldier), (god bless america flag), (bombed destroyed desolate abandoned city background)
Ajustes
Sampler
LCM
Pasos
13
Guidance
2
Semilla
34243121347290
Tamaño
1024x1024
Prompt
(shrek fighter jet pilot in the cockpit of a fighter jet)
Ajustes
Sampler
DPM++ 2M SDE Karras
Pasos
16
Guidance
3.5
Semilla
3941127207
Tamaño
512x768
Prompt
scrletroxl, butterflies, skin burns, scarlet rot, orange theme, red theme, photography of a cute fairy, big eyes, intricate details, realism, colorful cyberpunk <lora:scrletroxl-step00000350:1>
Prompt negativo
bad quality, bad anatomy, worst quality, low quality, low resolution, extra fingers, blur, blurry, ugly, wrong proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy, child, loli, underage, teen, young, young face, loli face, lolicon, flat chest, child, children, cub, small, short ,babyface, tiny, nude, naked, bad hands, bad face, deformed face,
Ajustes
Sampler
DPM++ 2M SDE Karras
Pasos
60
Guidance
7
Semilla
1089233400922836
Tamaño
1024x1024
Prompt
modisn disney, (dark magic), (grim), mermaid, masterpiece, best quality, (intricate details), dreamy, perfect eyes, dark pupils, magnificent, ethereal, volumetric lighting, lightroom, ((cinematic)), raytracing, subsurface scattering, face focus, DSLR, HDR, HD.
Prompt negativo
low quality, error, weird, blur, blurry
Ajustes
Sampler
DPM++ 2M Karras
Pasos
30
Guidance
7
Semilla
286892591507420
Tamaño
1024x1024
Prompt
princess rosalina, village scenery, absolutely outstanding image
Ajustes
Sampler
LCM
Pasos
13
Guidance
2
Semilla
700954165701230
Tamaño
768x1344
Prompt
(nuclear bomb explosion mushroom cloud american flag shape red white and blue stars and stripes, destroyed city desolate abandoned ground)
Ajustes
Sampler
DDPM Simple
Pasos
30
Guidance
4
Semilla
898271112465747
Tamaño
2048x2048
Prompt
modisn disney (disney pixar style:1.2) (cute adorable girl:1.1) (adult age 25:1.25) short hotpink hair, sexy smile, bright blue eyes, thin and fit, large breasts, standing in her house, wearing a plain simple white tank top, dynamic lighting, subpixel rendering, well lit
Prompt negativo
bad quality, bad anatomy, low resolution, ugly, deformed, (watermark, logo, text:1.15), (mickey mouse:1.2)
Modelos de IA para generar imagen, vídeo y texto
modern disney3 xl es un modelo base para la familia Stable Diffusion XL 1.0 listado en ModelTrends.ai, un catálogo de solo lectura de modelos de IA de imagen, vídeo y texto de código abierto. Compáralo con otros modelos Stable Diffusion XL 1.0, consulta su puntuación de calor para ver su tendencia y ábrelo en PirateDiffusion o BitVector para probarlo.
Explorar por familia de modelos
Ver todos los modelos