Model
Trends
.ai
Model
Trends
.ai
los mejores modelos de IA de código abierto
Ejecutar en local
etherMoonlightMix_beta2.safetensors
1.99 GB · SafeTensor · fp16 · pruned
kl-f8-anime2.safetensors
386 MB · SafeTensor
Descargar
Las descargas las sirve Civitai. Algunos creadores piden iniciar sesión en Civitai primero.
AD
<ether-moonlight-b2>
Sobre este modelo
STABLE DIFFUSION 1.5 · Modelos base
Creado por
gamerdan69
en Civitai
★ 🌙 Hello, this is Ether Moonlight Mix by GamerDan69 🌙 ★ A fun little anime style model designed to replicate one of my favorite mediums - oil paintings! Please keep in mind that this model has biases in generating females and humans. ✨ Please Share Your Cool Creations! ✨ * Beta 2 Still figuring out the direction of the model. Used Ether One for a more generalized base model. Focused on having faces and general aesthetic be more 'anime-like' while retaining the rough, oil painting inspired texture.
Notas del creador
★ 🌙 Hello, this is Ether Moonlight Mix 🌙 ★ A fun little anime style model designed to replicate one of my favorite mediums - oil paintings! Please keep in mind that this model has biases in generating females and humans. ✨ Please Share Your Cool Creations Below! ✨ * Beta 3 Updated Ether One and added a pinch of Ether Blu 7 to increase vibrancy, as well as making illustrations more expressive. Lots of weight changes designed to further refine the painterly style. Tuned faces to be a little more semi-realistic, though still very much anime. Finished off with some LORA's to compliment the overall style. Feedback will be appreciated! I recommend utilizing words that describe mediums, such as oil painting, watercolor, gouache, which can further enhance the painterly effect. Additionally, evoking painters can do similar things. Try great painters and illustrators such as John Singer Sargent, Dean Cornwell and Anders Zorn. are a great way to both tune the style of your outputs and learn more about art. ☄️ Generation Recommendations Use whatever sampler, steps, CFG you prefer. Most sample images were generated with: - Sampler: DPM++ 2M Karras - Steps: 20 - 28 - CFG: 7 - 11 - Clip Skip: 1 - ENSD: 31337 Higher CFG can lead to more vibrant results. Negative Prompt Example: "NSFW, (worst quality, low quality:1.3), signature" I recommend this simple negative prompt if you wish to achieve a similar style to the sample images. Sample images were further upscaled using AUTO1111 Hi-res fix. Please utilize it if you wish to achieve similar results. - Latent (nearest-exact) - Upscale by: 2 - Denoising strength: 0.55 Are your results changing too much after Hi-res fix? Please try (Also recommended for simple style illustrations, anime, cartoon, etc.) - 4x-foolhardy-Remarci - Upscale by: 2 - Denoising strength: 0.45 - 0.55 Recommended VAE: The VAE is baked. Strongly recommended as the model was tuned with this specific VAE's colors and saturation in mind. 🖊️ Prompting Advice As this is an anime style model I tuned it with booru style tag prompting, 1girl, long hair, jacket, etc. Of course you're free to prompt however you like. Mixing tags with prose can lead to fun results. Utilizing words that describe mediums, such as oil painting, watercolor, gouache, can further enhance the painterly effect. Additionally, evoking painters can do similar things. Try great painters and illustrators such as John Singer Sargent, Dean Cornwell and Anders Zorn. are a great way to both tune the style your outputs and learn more about art. If you look at the prompts included with the sample images they demonstrate that even with a very loose and vague style of prompting you can achieve fun, high quality images. Try mixing natural language and booru-styled tags. Experiment and give the AI some freedom to interpret your ideas! General guidelines: - Prompt in the style of anime/booru-style models, "masterpiece, best quality, ..... " - More anime style images, stronger bias towards females/humans - Prompt in the style of photography/non-anime models, "professional photograph of ..... " - More realistic images, higher style variety 📘 Model Merging Info - Beta 3 I have no training or real knowledge of machine learning. I merged the model using the information provided on as well as the ones in I very arbitrarily mixed the UBM weights of each model, modifying the values with trial and error until I was visually satisfied with it. I utilized the extension for AUTO1111 by hako-mikan. Please refer to the 'About This Version' for more detailed information. 💙 Credits Thank you to WarriorMama777 for providing and other various mixes as well as detailing your workflow which inspired me to try mixing my own models. Thank you to hako-mikan for creating the extension allowing a quicker workflow for merging. Thank you to those that have contributed to these Thank you to gsdf, rqdwdw for creating Thank you to Xerxemi and Xynon for Thank you to Mushroom for Thank you to Yang for Thank you to Someone97421 for and Thank you to Aotsuyu for Thank you to OliviaOliveira for Thank you to those at the for their archive of SD LORA's and checkpoints. Thank you to AUTO1111 for creating the web UI. Thank you to StabilityAI for starting everything with Stable Diffusion. Thank you to CivitAI and Huggingface for providing places where open source AI can flourish. Thank you to the entire SD community for continuing to openly share and create.
Palabras de activación
oil painting
watercolor
John Singer Sargent
Dean Cornwell
Anders Zorn
1,166 descargas · 89 me gusta en Civitai
SHA256
C73944F7409DBBA05E3F16762C3C4FD6B43C82E4FF640DB518DE6ADE5F00676D
ID de modelo de ModelTrends.ai
#8977
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
UniPC
Pasos
50
Guidance
8
Semilla
929947023
Tamaño
640x960
Prompt
oil painting, a skull with a flowers growing from it, sharp detailing, masterpiece, 8k, HDR, best quality, detailed skin, extremely detailed, detailed shadows, shading, <lora:GoodHands-beta2:1>
Prompt negativo
asian, (blurry:1.1), watermark, trademark, logo, child, loli, childlike, cropped, (low quality, worst quality:1.3), (easynegative), (bad-hands-5), (negative_hand-neg), BadDream, ng_deepnegative_v1_75t, UnrealisticDream, (bad_prompt_version2), verybadimagenegative_v1.3, (deformed fingers), (deformed hands), (mangled fingers), fused fingers, (extra fingers, deformed hands, polydactyl), (myself-badhand-v5), ERA09NEGV2, NegfeetV2
Ajustes
Sampler
DPM++ 2M Karras
Pasos
20
Guidance
9
Semilla
2417817836
Tamaño
512x832
Prompt
(masterpiece, best quality, highly detailed, intricate), a walkway in a garden with lots of green plants and trees on either side of it and a lantern hanging from the ceiling, Florence Engelbach, tone mapping, a flemish Baroque, german romanticism, cinematic composition, beautiful lighting
Prompt negativo
NSFW, (worst quality, low quality:1.3)
Ajustes
Sampler
DPM++ 2M Karras
Pasos
30
Guidance
16
Semilla
3080474982
Tamaño
512x768
Prompt
(best quality, masterpiece, ultra-detailed, high resolution:1.2), oil painting, high quality artwork, woman, female angel, angel wings, large feather wings, short blonde hair, walking over water, transfiguration, sun rays, god rays, clouds, ocean, blue sky, (style of Winslow Homer:1.1) <lora:tools/colorize> <lora:tools/epiNoiseoffset_v2>
Prompt negativo
mountians, island, land, building, roof, tower, arc, (worst quality, low quality, bad quality:1.3), embedding:ng_deepnegative_v1_75t, embedding:EasyNegative, embedding:badhandv4, embedding:imageSharpener
Ajustes
Sampler
DPM++ 2M Karras
Pasos
30
Guidance
16
Semilla
3580786058
Tamaño
512x768
Prompt
masterpiece, detailed, beautiful, oil painting, 1girl, empress, royal tiara, wearing a white furcoat, white fur, riding a white horse outside in the snow, pine forest, romantic, magical, fantasy, falling star, seductive, cleavage, large breasts, short blonde hair, laced hair, smiling BREAK red leather boots, red gloves, red scarf <lora:epiNoiseoffset_v2>
Prompt negativo
(building, castle:1.2), (worst quality, low quality, bad quality:1.3), embedding:ng_deepnegative_v1_75t, embedding:EasyNegative, embedding:badhandv4, embedding:imageSharpener
Ajustes
Sampler
DPM++ 2M Karras
Pasos
20
Guidance
9
Semilla
3949671521
Tamaño
512x832
Prompt
masterpiece, best quality, realistic, detailed background, the forgotten city made of white marble, grand, epic, fantasy, mystical, sunbeam, soft lighting, volumetric lighting, dramatic
Prompt negativo
NSFW, (worst quality, low quality:1.3)
Ajustes
Sampler
DPM++ 2M Karras
Pasos
20
Guidance
9
Semilla
2575951989
Tamaño
512x832
Clip skip
2
Prompt
masterpiece, best quality, girl standing under the dead tree, black and red palette, eerie
Prompt negativo
NSFW, (worst quality, low quality:1.3)
Ajustes
Sampler
DPM++ 2M Karras
Pasos
20
Guidance
9
Semilla
3591699861
Tamaño
512x832
Prompt
(masterpiece, best quality, highly detailed, intricate), a walkway in a garden with lots of green plants and trees on either side of it and a lantern hanging from the ceiling, Florence Engelbach, tone mapping, a flemish Baroque, german romanticism, cinematic composition, beautiful lighting
Prompt negativo
NSFW, (worst quality, low quality:1.3)
Ajustes
Sampler
DPM++ 2M Karras
Pasos
30
Guidance
16
Semilla
542196208
Tamaño
960x640
Prompt
(best quality, masterpiece, ultra-detailed, high resolution:1.2), oil painting, high quality artwork, woman, angel wings, large feather wings, short blonde hair, walking over water, transfiguration, sun rays, god rays, clouds, ocean, blue sky, (style of Winslow Homer:1.1) <lora:tools/colorize> <lora:tools/detail_slider_v4> <lora:tools/epiNoiseoffset_v2>
Prompt negativo
mountians, island, land, building, roof, tower, arc, (worst quality, low quality, bad quality:1.3), embedding:ng_deepnegative_v1_75t, embedding:EasyNegative, embedding:badhandv4, embedding:imageSharpener
Modelos de IA para generar imagen, vídeo y texto
ether moonlight b2 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