Nova Flat XL
Nova Flat XL is Anime SDXL checkpoint that aims to have flat style: not flat coloring
All images on example were created with diffusers with custom png tags
Rules
You cannot use the generated images for commercial use if it's not edited (or just turning it to black and white)
You can share images without any restriction if you don't monetize it
Advertising this model to outside is always welcome
Recommend Settings
Sampler: Euler a
Steps: 20~30
Clip Skip: 1-2
Denoising Strength: 0.65 - 0.8
CFG Scale: 4~6
Prompt: masterpiece, best quality, amazing quality, 4k, very aesthetic, high resolution, ultra-detailed, absurdres, newest, scenery, {Prompt}, BREAK, depth of field, volumetric lighting
Negative Prompts: modern, recent, old, oldest, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured, long body, lowres, bad anatomy, bad hands, missing fingers, extra digits, fewer digits, cropped, very displeasing, (worst quality, bad quality:1.2), sketch, jpeg artifacts, signature, watermark, username, signature, simple background, conjoined, bad ai-generated
Description
Initial version (epred)
FAQ
Comments (15)
Is this based on Noob or Illustrious?
It says "epred" so I'm guessing Noob?
The base is NoobAI but since Noob is the extend of Illustrious, I document the base model as Illustrious
@Crody Yeah it's correct to pick Illustrious as the base model since Noob doesn't have its own category on Civitai, I just like to know what the real base model is, it matters in some cases, with some LoRa interactions or for merges.
thanks for the model man. great work as always. looks great. :)
我是一位新手。我几乎完全照搬了例图的提示词，也遵循了推荐的设置，但不知为何，我的图片看上去是褪色的
I’m a beginner. I pretty much copied the prompt from the example and followed the recommended settings, but for some reason, my image looks washed out.
我似乎是少数遇到问题的人？但至少模型是不错的
It seems like I might be one of the few who encountered this issue? But at least the model itself is good.
@qianshangyuan9717 VAE?
@lamfong223648 我试过sdxlVAE，但似乎没有改变结果
I've tried sdxlVAE, but it doesn't seem to have changed the results.
what UI u using?
@lamfong223648 forge
@lamfong223648 oh, I have solved the problem! The model is pretty great!
@qianshangyuan9717 :D
你的機翻中文是怎麽回事？
Why did you make your words so weird as if they were translated with a poor g**gle.
@qianshangyuan9717 How did you fix this? I'm having problems with this creator's other models as well.
This model gave me most interesting pictures out of all Novas using same prompts. Looks like underappreciated model, it's very creative. Clip skip 1 seems to work better than 2, less artifacts with faces.