Ejecutar en local
surfboard_sit_REALISM-000023.safetensors
218 MB · SafeTensor
Las descargas las sirve Civitai. Algunos creadores piden iniciar sesión en Civitai primero.
Sobre este modelo
STABLE DIFFUSION XL 1.0 · LoRAs
Surfboard Sit | Pony + Animagine by aigenerator456. Difference between Pony v2 and Pony v3: Pony v3: overall better, with better training data, but may be less consistent at producing a cohesive image Pony v2: trained longer and more likely to produce a cohesive image, but high change it will burn your image / ruin your character's eyes, especially on higher CFG I recommend using Pony v3 first and switching to v2 if you really cant get v3 to do what you want. Keywords: surfboard_straddle, front view, surfboard surfboard_straddle, side view, surfboard surfboard_straddle, view from behind, surfboard Pony V3 & Animagine: Weight: 0.7 - 0.8 | Higher = more likely to be sitting on the surfboard in a way that makes sense, but risk of burning the image Pony V2: Weight: 0.5 to 0.7 (Higher = stronger, more consistent but negative effect on image quality) dont be afraid to go even lower than 0.5.
Notas del creador
V4 Update:
Complete overhaul of the dataset and training. The previous versions of this model had a significant negative impact on image quality, especially when using art style LoRAs. This version is much much better at preserving style and working together with style LoRAs and finetunes of Pony.
PonyRealism Notes:
The PonyRealism LoRA destroys faces, you will need to use Civitai's Face Fix option or ADetailer / Face Detailer to restore faces.
Keywords:
-
surfboard_straddle, surfboard
-
surfboard_straddle, surfboard, front view
-
surfboard_straddle, surfboard, side view
-
surfboard_straddle, surfboard, view from behind
Other useful words:
-
ocean
-
negative prompt: sand
Keywords explanation:
Use the keywords "surfboard_straddle, surfboard" to get a random angle, this is the most flexible keywords and can enable you to get more unique angles
Add the keywords "front view", "side view", "view from behind" to lock the camera to a specific angle. If you use these, the model usually won't play nicely with other camera descriptors. Eg "low angle" combined with "front view" will result in a bad output usually.
Weight: 0.7 - 0.8
Higher weight = more likely to be sitting on the surfboard in a coherent way, but stronger negative effect on art style.
Palabras de activación
surfboard_straddle, surfboard
surfboard_straddle, surfboard, side view
surfboard_straddle, surfboard, front view
surfboard_straddle, surfboard, view from behind
SHA256
B45DE90EC858932522A0ECB646B1F8E337395A5C1DC69E194E62C962D63D3107
ID de modelo de ModelTrends.ai
#3658
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
DPM++ 2M Karras
Pasos
40
Guidance
7
Tamaño
2048x2048
Prompt
score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up, surfboard, surfboard_straddle, water, 1girl, beautiful, wetsuit, city, night, sunset
Prompt negativo
score_4, score_5, score_6
Ajustes
Sampler
DPM++ 2M Karras
Pasos
40
Guidance
7
Tamaño
2048x2048
Prompt
score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up, surfboard, surfboard_straddle, water, 1girl, beautiful, wetsuit, city, night, sunset
Prompt negativo
score_4, score_5, score_6
Modelos similares
Modelos de IA para generar imagen, vídeo y texto
surfboard xl es un LoRA 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.
Más modelos Stable Diffusion XL 1.0Más LoRAs de Stable Diffusion XL 1.0ponytypeobjectsanimeeffectsconcept
Explorar por familia de modelos
Modelos Text / LLM
411
Modelos Anima
509
Modelos Chroma
14
Modelos Flux
1,071
Modelos Flux 2 / Klein
1,237
Modelos MiniMax H3
331
Modelos Hunyuan
197
Modelos Ideogram
20
Modelos Krea2
674
Modelos Qwen
17
Modelos Qwen2
36
Modelos Ltx2
150
Modelos Stable Diffusion 1.5
6,465
Modelos Stable Diffusion XL 1.0
15,432
Modelos Zimage
804
Modelos Wan
919

Model
Trends
.ai
© ModelTrends.ai
|
Hecho en Japón
|
© 2026
