Model
Trends
.ai
Model
Trends
.ai
los mejores modelos de IA de código abierto
Ejecutar en local
anyloraCheckpoint_bakedvaeBlessedFp16.safetensors
1.99 GB · SafeTensor · fp16 · pruned
Las descargas las sirve Civitai. Algunos creadores piden iniciar sesión en Civitai primero.
Sobre este modelo
STABLE DIFFUSION 1.5 · Modelos base
Creado por
Lykon
en Civitai
AnyLoRA by Lykon. an anime base model that doesn't work with every lora. The "Any" part refers to the Anything series of anime base models, and that's what it's most commonly used for. Created by Lykon, the same model creator that makes Dreamshaper, AnyLora focuses on high compatibility with many anime LoRAs in a safe range of aesthetics. Works well with other models by Lykon, like
Notas del creador
AnyLoRA Add a ❤️ to receive future updates. Do you like what I do? Consider supporting me on 🅿️ or feel free to ☕ For LCM read the version description. Available on the following websites with GPU acceleration: - Remember to use the pruned version when training (less vram needed). Also this is mostly for training on anime, drawings and cartoon. I made this model to ensure my future LoRA training is compatible with newer models, plus to get a model with a style neutral enough to get accurate styles with any style LoRA. Training on this model is much more effective compared to NAI, so at the end you might want to adjust the weight or offset (I suspect that's because NAI is now much diluted in newer models). I usually find good results at 0.65 weigth that I later offset to 1 (very easy to do with ComfyUI). This is good for inference (again, especially with styles) even if I made it mainly for training. It ended up being super good for generating pics and it's now my go-to anime model. It also eats very little vram. Get the pruned versions for training, as they consume less VRAM. Make sure you use CLIP skip 2 and booru style tags when training. Remember to use a good vae when generating, or images wil look desaturated. Or just use the baked vae versions.
8,702 descargas · 1,334 me gusta en Civitai
SHA256
5353D90E0CA5FAB82D0448BF94A1A016C404F9E5F8A3F12A22F4F4E3BE5D68C6
ID de modelo de ModelTrends.ai
#374
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 SDE Karras
Pasos
20
Guidance
7
Semilla
1730459089
Tamaño
512x512
Prompt
<lora:Bibble-10:0.7>, (masterpiece, best quality, absurdres, perfect anatomy, good face), 1boy, miniboy, male focus, Bibble, creature, blue eyes, blue skin, purple fur, eyelashes, colored skin, pink hair, short hair, polka dot, blue fur, multicolored fur, pointy ears, furry, furry male, wings, fairy wings, sunglasses, leather jacket, backpack, armband, sneakers, high tops, facing viewer, looking at viewer, full body, laughing, open mouth, happy, surfing, riding, hover board, motion lines, motion blur, chasing, police car, centered, future, cyberpunk, skyline, cityscape, city, flying car, hovercraft, sky, billboard, holographic monitor, chinese text, blade runner, barbie movies, barbie \(franchise\), barbie fairytopia \(film series\)
Prompt negativo
<embedding:SimpleNegativeV3>, <embedding:FastNegativeV2>, <embedding:negative_hand-neg>, <embedding:bad-artist>, <embedding:bad_prompt_version2-neg>, <embedding:NegFeetV2>, SimpleNegativeV3, FastNegativeV2, negative_hand-neg, sketch By bad artist, bad_prompt_version2-neg, NegFeetV2, worst quality, low quality, lowres, blurry, old, unprompted nsfw, 1girl, otoko no ko, jpeg artifacts, cropped, cropped arms, cropped legs, cropped head, beard, flower, crying, tears, grass, whiskers, cat, tail, holding, 3d animation, 3d \(artwork\), gloves, realistic, pale skin, albino
Ajustes
Sampler
DPM++ 2M SDE Karras
Pasos
20
Guidance
7
Semilla
559059091
Tamaño
512x512
Prompt
<lora:Bibble-10:0.8>, (masterpiece, best quality, absurdres, perfect anatomy, good face), avatar icon, 1boy, miniboy, solo, male focus, solo focus, Bibble, creature, blue eyes, blue skin, purple fur, eyelashes, colored skin, pink hair, short hair, polka dot, blue fur, multicolored fur, pointy ears, furry male, furry, wings, fairy wings, facing viewer, sitting, bench, park, park bench, reading, newspaper, embarassed, flustered, frown, open mouth, full body, no humans, sunglasses, skyline, cityscape, urban, high tops, sneakers, 1980s \(style\), barbie movies, barbie \(franchise\), barbie fairytopia \(film series\)
Prompt negativo
<embedding:SimpleNegativeV3>, <embedding:FastNegativeV2>, <embedding:negative_hand-neg>, <embedding:bad-artist>, <embedding:bad_prompt_version2-neg>, <embedding:NegFeetV2>, SimpleNegativeV3, FastNegativeV2, negative_hand-neg, sketch By bad artist, bad_prompt_version2-neg, NegFeetV2, worst quality, low quality, lowres, blurry, old, unprompted nsfw, 1girl, otoko no ko, jpeg artifacts, cropped, cropped arms, cropped legs, cropped head, beard, flower, crying, tears, grass, whiskers, cat, tail, holding, 3d animation, 3d \(artwork\), glasses
Ajustes
Sampler
DPM++ 2M SDE Karras
Pasos
20
Guidance
7
Semilla
1730459089
Tamaño
512x512
Prompt
<lora:Bibble-10:0.7>, (masterpiece, best quality, absurdres, perfect anatomy, good face), 1boy, miniboy, male focus, Bibble, creature, blue eyes, blue skin, purple fur, eyelashes, colored skin, pink hair, short hair, polka dot, blue fur, multicolored fur, pointy ears, furry, furry male, wings, fairy wings, sunglasses, leather jacket, backpack, armband, sneakers, high tops, facing viewer, looking at viewer, full body, laughing, open mouth, happy, surfing, riding, hover board, motion lines, motion blur, chasing, police car, centered, future, cyberpunk, skyline, cityscape, city, flying car, hovercraft, sky, billboard, holographic monitor, chinese text, blade runner, barbie movies, barbie \(franchise\), barbie fairytopia \(film series\)
Prompt negativo
<embedding:SimpleNegativeV3>, <embedding:FastNegativeV2>, <embedding:negative_hand-neg>, <embedding:bad-artist>, <embedding:bad_prompt_version2-neg>, <embedding:NegFeetV2>, SimpleNegativeV3, FastNegativeV2, negative_hand-neg, sketch By bad artist, bad_prompt_version2-neg, NegFeetV2, worst quality, low quality, lowres, blurry, old, unprompted nsfw, 1girl, otoko no ko, jpeg artifacts, cropped, cropped arms, cropped legs, cropped head, beard, flower, crying, tears, grass, whiskers, cat, tail, holding, 3d animation, 3d \(artwork\), gloves, realistic, pale skin, albino
Ajustes
Sampler
DPM++ SDE Karras
Pasos
25
Guidance
7
Semilla
3020654048
Tamaño
512x768
Clip skip
2
Prompt
masterpiece, best quality, ultra-detailed, illustration,(1girl),beautiful detailed eyes, looking at viewer, close up, pink hair, shy, cat ears
Prompt negativo
FastNegativeV2
Ajustes
Sampler
Euler a
Pasos
20
Guidance
7
Semilla
2365979184
Tamaño
512x768
Clip skip
2
Prompt
<lora:grey_leggings_v0.1:1> 1girl, yoga pants, grey pants, ponytail, black hair, looking at viewer, mirror, reflection,, masterpiece, best quality, highly detailed
Prompt negativo
(worst quality, low quality:1.4)
Ajustes
Sampler
Euler a
Pasos
20
Guidance
7
Semilla
1146953986
Tamaño
512x768
Clip skip
2
Prompt
(masterpiece,best quality), (HDR, UHD, 8K,best quality,masterpiece,Highly detailed,Studio lighting,ultra-fine painting,sharp focus,physically-based rendering,extreme detail description,Professional,Vivid Colors), <lora:ttniji:1>,ttniji,1girl, solo,flower, border,cowboy shot, parted lips, looking at viewer, grey eyes, multicolored background, gradient background, chinese clothes, east asian architecture, depth of field, own hands together, light particles, film grain, <lora:ttoldstyle:0.5>,ttos, <lora:Heavy_grain:0.5>,film overlay, <lora:pingmian:0.5>,pingmian,text, <lora:add_detail-2-2:0.5>
Prompt negativo
EasyNegative, badhandv4, negative_hand, child, young, teenager, lowres, bad anatomy, bad hands, error, missing fingers, extra digit,extra legs, fewer digits, cropped, signature, watermark, username,bad feet, bad face, missing eye, missing teeth, wavy mouth, three hands, color lump,
Ajustes
Sampler
Euler a
Pasos
20
Guidance
7
Semilla
48189673
Tamaño
512x768
Clip skip
2
Prompt
<lora:grey_leggings_v0.1:1> 1girl, yoga pants, skin tight, looking back, sky,, masterpiece, best quality, highly detailed
Prompt negativo
(worst quality, low quality:1.4)
Ajustes
Sampler
Euler a
Pasos
20
Guidance
7
Semilla
1887903259
Tamaño
512x768
Clip skip
2
Prompt
<lora:foreground_boys_v1.5:1> 1girl, long hair, looking back, upper body, 2boys, kiss, old man, surprised,, masterpiece, best quality, highly detailed
Prompt negativo
(worst quality, low quality:1.4)
Modelos de IA para generar imagen, vídeo y texto
anylora es un modelo base para la familia Stable Diffusion 1.5 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 1.5, 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