Model
Trends
.ai
Model
Trends
.ai
the best open source ai models
Run Locally
canvasdarkxl_v10.safetensors
6.57 GB · SafeTensor · fp16 · full
sdxl_vae.safetensors
319 MB · SafeTensor
Download
Downloads are served by Civitai. Some creators ask for a Civitai login first.
AD
Install / Run on Graydient
Requires membership
<canvasdark-xl>
About This Model
STABLE DIFFUSION XL 1.0 · Base Models
Created by
TridIsntAName
on Civitai
Copax Dark XL y TridInstAName writes: Using art from Honkai: Star Rail, Scenes of Arcane and many more, CanvasDark specialises in punkish, edgy and broody imagery with realistic lighting. Its strength in backgrounds allows for painting-like sceneries that complete your badass characters with the lightning, blood moon and dark castles you see in every Castlevania game! Recommended Negative Prompt: (RESULTS WILL VARY DRASTICALLY IF YOU USE A DIFFERENT NEGATIVE PROMPT!!! LESS IS MORE!) [normal quality] [[low quality, worst quality]] If the model's results are too realistic add [[photorealistic, photorealism]] Recommended Settings: /sampler:dpm2m /karras /steps from 35-45 on average for optimal results. /guidance from 8-12 recommended. Starting at 13 eyes can start looking weird.
Creator notes
Using art from Honkai: Star Rail, Scenes of Arcane and many more, CanvasDark specialises in punkish, edgy and broody imagery with realistic lighting. Its strength in backgrounds allows for painting-like sceneries that complete your badass characters with the lightning, blood moon and dark castles you see in every Castlevania game! Recommended Negative Prompt: (RESULTS WILL VARY DRASTICALLY IF YOU USE A DIFFERENT NEGATIVE PROMPT!!! LESS IS MORE!) -normal quality, (low quality, worst quality:1.3) If the model's results are too realistic for your tastes, use this one instead: -normal quality, (low quality, worst quality:1.3), photorealistic, photorealism Recommended Settings: -DPM++ 2M Karras, DPM++ 3M SDE Karras and DMP++ 2M Exponential are my favourite samplers for this model. If you use ComfyUI, I recommend using DPM++ 2M Karras, then DPM++ 3M SDE Karras for the second pass. -I use 35-45 steps on average for optimal results. -CFG from 8-12 recommended. Starting at CFG 13 eyes can start looking weird. -I prefer 4x_BooruGan_650k, 0,32-0,4 denoise and 20 hires steps. Nearest, Anime6B are also good options. -I prefer Anime6B upscaler for SD Upscale. -Don't use Restore Faces. I waited 13 minutes per image to provide you usable metadata. Please appreciate my efforts. ;-;
765 downloads · 130 likes on Civitai
SHA256
ED2842EE59A7CBAC939F9A855B0CEB9497BCB93421985A1B6318C24A5B779C6D
ModelTrends.ai Model ID
#9115
Flag content
Example renders
Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.
Settings
Sampler
DPM++ 2M Karras
Steps
35
Guidance
10
Seed
3358480025
Size
1024x1024
Prompt
dark theme, spiky hair, messy hair, crimson hair, two tone hair, red hair, ruby eyes, pale skin, dark cloak, dark, dark castle, 1girl, from side, chin up, centered, one arm raised,
Negative prompt
worst quality, (low quality, normal quality:1.3)
Settings
Sampler
Euler
Steps
36
Guidance
7
Seed
1475335069
Size
832x1216
Prompt
pretty
Settings
Sampler
DPM++ 2M Karras
Steps
35
Guidance
10
Seed
3046175338
Size
1024x1024
Prompt
stelle \(honkai: star rail\), sitting in a tent in a snowscape, her expression is cool and emotionless
Negative prompt
normal quality, (low quality, worst quality:1.3)
Settings
Sampler
DPM++ 2M Karras
Steps
35
Guidance
10
Seed
4265417321
Size
1024x1024
Prompt
dark theme, from side, from below, leaning against wall, neon signs, city, people in background, denim pants, street, white hair, expressionless, mature female, midriff, high ponytail, red eyes, necklace, earrings, bracelet, long sleeves, belt, looking at viewer, head tilt
Negative prompt
worst quality, (low quality, normal quality:1.3), photorealism
Settings
Sampler
DPM++ 2M Karras
Steps
35
Guidance
6
Seed
3046175338
Size
832x1156
Prompt
emerald, vines, tree, emerald embedded into tree
Negative prompt
normal quality, (low quality, worst quality:1.3)
Settings
Sampler
DPM++ 2M Karras
Steps
35
Guidance
10
Seed
3086370642
Size
1024x1024
Prompt
a girl with a sword and a dark cloak with it's hood up, holding a sword in her hand and a red light shining on her face, she is standing in front of a castle, in a bleak, withered garden, her expression is cold and ruthless, her eyes squinted, gothic art, BREAK, 1girl, bangs, black hoodie, blood, blood on clothes, blood on face, blood on hands, blood on weapon, blood splatter, cloak, eyebrows visible through hair, gloves, holding, holding sword, holding weapon, hood, hood up, hooded coat, hoodie, long hair, looking at viewer, red eyes, solo, sword, weapon, blonde hair
Negative prompt
worst quality, (low quality, normal quality:1.3)
Settings
Sampler
DPM++ 2M Karras
Steps
35
Guidance
10
Seed
1354335926
Size
1024x1024
Prompt
sitting on a rock inside of a river, her brown hair flowing in the wind, fishes swim by her around the stone, and a waterfall feeds into the river, vegetation and moss surrounds her, trees in the distance, bushes around them, moss on the stone, anime art, atmospheric lighting, focus on characters expression
Negative prompt
worst quality, (low quality, normal quality:1.3)
AI Models for Image, Video & Text Generation
canvasdark xl is a base model for the Stable Diffusion XL 1.0 family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Stable Diffusion XL 1.0 models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.
Browse by Model Family
Browse all models