Diffus
시작하기
모델/NightVisionXL - NightVisionXL_v9.0.0

NightVisionXL - NightVisionXL_v9.0.0

socalguitarist
|
8/8/2025
|
11:16:37 PM
| Discussion|
0
A hooded wizard holding a glowing magic orb, standing on rocky terrain with mystical golden fire swirling behind him and an ethereal night sky above the mountainous landscape.
A humanoid robot with glowing red lights stands on a rain-soaked, neon-lit alleyway surrounded by potted plants and dystopian building facades in a cyberpunk atmosphere.
Portrait of Wonder Woman rendered in cyan and blue tones with comic art style on a beige background.
Close-up portrait of a woman with vivid red hair, bright blue eyes, and freckles, created with mixed media including crayon, colored pencil, and color pen.
A detailed cybernetic creature with a glowing pink and yellow visor helmet surrounded by wires and tubes, set against a dark neon-lit background.
Dark fantasy landscape with tall star-thistle trees glowing with constellation-like leaves and swirling roots, under a vibrant cosmic magenta-indigo sky.
A dark hooded wizard stands on rocky terrain holding a fiery staff with glowing orange flames, surrounded by vibrant green and yellow mystical light and smoke.
A colossal biomechanical hybrid with glowing orange eyes looms over a lone human figure standing in a dark, eerie landscape illuminated by fiery light.
Two giraffes stand peacefully on a savanna with sparse trees, rendered in a dark fantasy style with bold ink outlines and watercolor textures, reminiscent of Frank Frazetta and World of Warcraft.
Outdoor portrait of a blonde woman in a flowing red dress, AI generated using Stable Diffusion.
Enchanted boat in a vibrant, fantastical swamp with glowing colors and mysterious atmosphere created using stable diffusion.
A fantasy rabbit warrior in medieval armor, generated using Stable Diffusion AI.

추천 네거티브 프롬프트

ugly, deformed, noisy, blurry, low contrast, cartoon, anime, drawing, low budget, cheap, bad quality

추천 매개변수

samplers

DPM++ 2M SDE AYS, DPM++ 2M SDE SGMUniform

steps

30

cfg

2.5

resolution

832x1216, 896x1152, 1024x1024

vae

baked VAE

추천 고해상도 매개변수

upscaler

4x-UltraSharp

upscale

1.5

steps

20

denoising strength

0.5

팁

Prompt NightVision XL like you would describe a scene to a human for best results.

Do NOT use SDXL refiner with NightVision XL as it reduces output quality.

Longer generation times are worth the higher quality and aesthetics.

버전 하이라이트

NightVisionXL V9.0.0 Release Notes

This is NightVisionXL 9.0 - This model is a fine tune of NightVision v8.1.1 with approx. 10,000 images comprising a rough mixture of 40% from a photography dataset, 40% from Laion Pop (filtered and recaptioned with GPTV), 10% from a cinematic dataset (same one used to train CineVisionXL), and 10% synthetic mixture of favorites picked from Civit and MJ, all hand chosen and captioned with GPTV. All input images were of high quality and large size, bucketed on training with a wide variety of sizes and aspect ratios, leading to a model that is very good at producing coherent output even in very extreme wide or tall aspect ratios, and anywhere in between. As with 8.1.1, NightVision v9.0 is a general purpose model that can output pretty much any style you like. NV continues to prefer natural language prompting over 1.5 style (though that does still work), however it has no Pony training or mixing, so those pony specific prompt rules won't work here (sorry).

I have not mixed in any speedups or improvements, nor any other alternate license models or LoRAs. NightVisionXL remains a pure SDXL model, and will stay that way moving forward.

Rather than my typical changelog (see above), I want to touch briefly on the release of SD3 Medium, the 2B model version. As a member of this community, I am very upset at the state of the model that was released. The hamfisted censorship of the model was uncalled for and effectively broke the model making training it almost impossible (from a technical standpoint it's just impossible to apply any type of decent learning rate without the loss skyrocketing and the train coming out completely terrible if not entirely broken). I know I've disappeared from the scene for awhile, I like many other trainers decided to "wait for SD3" - Now I regret that decision. This version of NightVision, this was my "private stock" version I trained for myself and my close friends. V8.1.1 was the swan song, v9 was my special gift to my friends, and it was those same friends who convinced me that v9 should be released, hopefully this can help bandage the wound that SD3 inflicted on the community. V9 isn't perfect, it has the same flaws that all SDXL models do (mostly related to the SDXL VAE, that I can't fix), but it's the best I've made, and now it's yours.

We'll see what happens with SD3. I'm going to say right now, unless there's a major training breakthrough with the 2B model, I'm likely just going to skip it and hold out for the 8B model (if they don't mangle that) or maybe look into training a different architecture, just not sure which one yet.

Known Issues

  • male genitalia is better, but still wierd. use a lora if you need perfect penises

  • hands are probably 85/90%, depending on the pose, but some things like holding objects can fight you.

  • Upside down or sideways faces (this is an SDXL VAE issue)

  • faces and detail at medium distance can be mushy in initial generations (another VAE issue)

크리에이터 스폰서

Like the work I do and want to say thanks? Buy me a coffee or Support me on Patreon for exclusive early access to my models and more!

Join us on SCG-Playground where we have fun contests, discuss model and prompt creation, AI news and share our art to our hearts content in THE FLOOD! 💖💖💖

NightVisionXL started as a lightly trained, photography focused SDXL model that specialized in photographic output. Over the past few months, NightVision has received dozens of trainings and tunings chasing the dragon that is pleasing aesthetic output. With the release of version 8.X, I feel like I'm much closer to my goal of effortless beautiful output that is aesthetically pleasing without requiring confusing negatives or comma separated nonsense.

NightVisionXL speaks natural language. Prompt it like you would describe a scene to a human being, and you'll be surprised by how well it can understand and comprehend your prompts.

I'm trying something new with V8 of NightVision, and I hope the results show in the output. I continue to scrape beautiful imagery that I think will train well, and this particular update is no exception with hundreds of beautiful license free AI images that I've sourced from MJ, Dalle3, Civit, Playground and my own outputs. On top of that, I'm also utilizing HF datasets for license free photography and the LAION-POP dataset, filtered to remove low quality images prior to training. Captioning is done using my own Spicy Burrito captioning tool (available to my Patreon subscribers on discord!) that creates incredibly verbose and effective captions that are essential for good coherent output.

On a final note, I've had multiple requests to "turbo-ize" this model. I have no plans to mix turbo into NightVision, as the licensing on NightVision is nice and open right now with the SDXL licensing, and I'd like to keep it that way. NightVision isn't fast, but I promise you the longer gen times are worth the wait!

This is NightVision XL, a lightly trained base SDXL model that is then further refined with community LORAs to get it to where it is now. NightVision XL has been refined and biased to produce touched-up photorealistic portrait output that is ready-stylized for Social media posting! NightVision XL has nice coherency and is avoiding some of the weird body issues and biases that are starting to plague some of the other photorealistic models. Further, NightVision XL produces rich deep blacks and great evening/night time scenes. It can also produce ridiculously bright output as well!

NightVision XL is capable of both SFW and NSFW output. As with all of my other models, tools and embeddings, NightVision XL is easy to use, preferring simple prompts and letting the model do the heavy lifting for scene building.

NOTE - This version includes a baked VAE, no need to download or use the "suggested" external VAE.

WARNING - DO NOT USE SDXL REFINER WITH NIGHTVISION XL

The SDXL refiner is incompatible and you will have reduced quality output if you try to use the base model refiner with NightVision XL.

Follow me here by clicking the heart ❤️ and liking the model 👍, and you will be notified of any future versions I release. I also need your help with feedback, please please please post your images and your honest feedback below, I will use your feedback and your output to help guide future revisions!

Follow me on IG!

Follow me on Threads!

Chat with me on Discord

Patreon coming soon!

이전
G0zeNA | Shiiro's Styles - v1.0
다음
SXZ Illuma - 2 Balanced
이 모델 사용하기

모델 세부사항

모델 유형

Checkpoint

기본 모델

SDXL 1.0

모델 버전

NightVisionXL_v9.0.0

모델 해시

b3cbfd20eb

제작자

socalguitarist's avatar
socalguitarist

토론

댓글을 남기려면 log in하세요.

NightVisionXL - NightVisionXL_v9.0.0 제작 이미지

A hooded wizard holding a glowing magic orb, standing on rocky terrain with mystical golden fire swirling behind him and an ethereal night sky above the mountainous landscape.
A humanoid robot with glowing red lights stands on a rain-soaked, neon-lit alleyway surrounded by potted plants and dystopian building facades in a cyberpunk atmosphere.
Portrait of Wonder Woman rendered in cyan and blue tones with comic art style on a beige background.
Close-up portrait of a woman with vivid red hair, bright blue eyes, and freckles, created with mixed media including crayon, colored pencil, and color pen.
A detailed cybernetic creature with a glowing pink and yellow visor helmet surrounded by wires and tubes, set against a dark neon-lit background.
Dark fantasy landscape with tall star-thistle trees glowing with constellation-like leaves and swirling roots, under a vibrant cosmic magenta-indigo sky.
A dark hooded wizard stands on rocky terrain holding a fiery staff with glowing orange flames, surrounded by vibrant green and yellow mystical light and smoke.
A colossal biomechanical hybrid with glowing orange eyes looms over a lone human figure standing in a dark, eerie landscape illuminated by fiery light.
Two giraffes stand peacefully on a savanna with sparse trees, rendered in a dark fantasy style with bold ink outlines and watercolor textures, reminiscent of Frank Frazetta and World of Warcraft.
Outdoor portrait of a blonde woman in a flowing red dress, AI generated using Stable Diffusion.
Enchanted boat in a vibrant, fantastical swamp with glowing colors and mysterious atmosphere created using stable diffusion.
A fantasy rabbit warrior in medieval armor, generated using Stable Diffusion AI.

architecture 이미지

A beautiful outdoor landscape featuring a stone house near a calm lake at sunset with mountains in the background, palm trees, blooming flowers, and a starry sky with a full moon and shooting stars.
A futuristic cityscape featuring tall concrete and cylindrical industrial structures enveloped in a dense foggy atmosphere with a minimalist white color scheme, and people walking in the foreground.
A red-haired girl with twin braids and a white dress sits happily on stone stairs outdoors, surrounded by three cats and greenery under a sunny sky.
Hyper-realistic close-up of a cow figure composed entirely of grass and purple flowers with detailed textures and dramatic lighting.
Aerial drone photo of an authoritarian city with towering skyscrapers, grand garden, palace and government buildings under cinematic lighting.
A full-body portrait of a steampunk catgirl with purple hair and sunset highlights standing on a grassy field with futuristic architecture and blue sky background.
A black cat sits on a wooden porch of a Japanese-style house, gazing at the glowing lantern and vibrant sunset over a peaceful garden and river landscape.
Hyper-realistic close-up of a female figure made of grass, moss, and red flowers, with detailed textures and vibrant natural elements.
A woman in a yellow biohazard suit stands on a rocky barren landscape facing a colossal dark sci-fi yellow sphere made of intertwined organic and mutated spheres, under an overcast sky.
An angel with yellow crystal-like hair seated on a tree branch under an arch, wearing a white dress and thigh-high stockings, with glowing halo and white wings against a blue sky.

기본 모델 이미지

Photorealistic scene of undead characters including zombies and skeletons walking through a spooky Halloween cemetery filled with glowing jack-o'-lantern pumpkins and desiccated trees in a dark, foggy atmosphere.

hyperrealism 이미지

A stunning aerial view of towering limestone cliffs illuminated by sunset light, surrounded by turquoise water and sandy beaches in Krabi.
Close-up portrait of a girl with striking yellow eyes and black bob-cut hair wearing a yellow hoodie with black patterns, adorned with tattoos and jewelry, holding her finger near her nose.
Portrait of a cyborg woman with flowing black hair, dressed in black clothing, showing intricate golden metallic robotic arms and parts of her mechanized body.
Portrait of an ethereal cyborg woman with pale skin, platinum-white hair, and piercing blue eyes, showing intricate mechanical details and a soft white background.
A hyperdetailed pastoral landscape featuring tranquil rural scenes with emerald green shadows, cadmium yellow highlights, and fractured indigo outlines under a cloudy sky.
Side profile of a human face and upper torso fragmented into irregular geometric shapes filled with vibrant colors on a black background
Intricate crowd of crackled glass humanoid figures in shades of ultramarine blue, blue gray, and rosegold speckles, featuring a kissing couple in the center, outdoors with water theme.
Portrait of a terrifying demon android with green and orange armor, set against an alien planetary backdrop with planets and a large ring structure, rendered in detailed hyperrealism with cubism influences.
A vast icy mountain range featuring a massive monolithic rock formation resembling a snarling face with a glowing turquoise-blue cavern mouth, a frozen river flowing into a snowy landscape, and two small silhouetted human figures on the right.
A female C-3PO with golden, battle-scarred armor and mechanical enhancements stands in a dense chaparral biome, holding a glowing war hammer and embracing a twisted tree branch under dim mystical light.

photography 이미지

Highly detailed, photorealistic depiction of a realistic Pikachu with fur texture, large black eyes, red cheeks, and standing on hind legs under cinematic lighting.
Close-up portrait of a blonde maid with blue eyes wearing a detailed black and white maid outfit and headdress, softly smiling with an innocent expression in front of a window with a city view.
Close up of an otter with sharp teeth and wet fur under black lighting, captured with long exposure using a 50mm lens on Kodak Portra 400 film
Futuristic cyborg girl with luminous neon white hair sitting cross-legged, viewed from below with mechanical limbs and glowing blue lighting in a dark cyberpunk city.
Blonde woman with freckles smiling and sitting outdoors wearing a maroon v-neck t-shirt and floral plated microskirt
Grandpa with gray hair and glasses in a light blue blazer and a young woman with gray hair in a deep pink dress, standing in a bright azure pool with a large white dog and a small kangaroo near a pastel pink wall.
Dark and moody modern architecture with tiered concrete structures illuminated by a warm orange glow at night, featuring fractured and glitch effects.
Side view of a bored face emoji figure wearing an orange hoodie, black jogger pants, and black high-top sneakers standing amidst blurred motion figures in a minimalistic open space.
Close-up portrait of a Korean man, 25 years old, with intense gaze, in a dark room lit by warm, moody lighting.
A mystical nighttime landscape featuring ancient ruins, a glowing golden moon, twinkling stars, rugged mountain valleys, and vibrant warm colors.

사진같은 이미지

Close-up of a highly detailed futuristic supercar featuring sleek design and cinematic lighting with film grain effects and shallow depth of field.
Anthropomorphic bat with bright green eyes and red hair leaning over a carved wooden bowl filled with orange petals, set against a rustic stone fireplace with cinematic lighting.
Realistic grey shrike perched on a branch with glowing iridescent feathers under low-key lighting and chiaroscuro effects
Photorealistic cityscape featuring a tall skyscraper illuminated at night with surrounding buildings and a mountain silhouette on a vibrant green background, rendered with cinematic lighting and metallic details.
An astronaut in a white spacesuit walks cautiously through tall, ruined abandoned buildings on a dusty desert planet with smoke rising in the background.
A mixed media collage of a cybernetic man with wings and long slender legs filled with photorealistic cityscapes and neon cyberpunk elements in a cinematic style.
Futuristic black and white image featuring metallic lines extending downward surrounded by dense foliage with red gradients and a blue pulsating diamond in the center.
Extreme closeup of a stunning oriental young woman's eye with dark eyeshadow, red lips, loose flowing black hair in a photorealistic watercolor style.