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
Configure the posing and details
NoobAI EPS v1.1 + Illustrious v2.0 stable DARE applied
FAQ
Comments (2)
All of variants Nova, Flat is my favourite series so far. V5.0 improve the colour and lighting so far in my testing.
Compared to other models, this one seems to require more negative prompts... Is it possible to exclude some negative material during training to reduce its impact? This affects the performance of Max Token Length.
Two models I often use are:
WAI SDXL iL v14:
bad quality, worst quality, worst detail, sketch, censor
Rouwei v0.8.0:
low quality, worst quality
They both require only short negative prompts to eliminate most finger or image quality issues.
I'm also experiencing some prompt contamination issues while training LoRa. I need to be aware of issues like prompts and negative prompts.
Of course, the problem isn't serious; it's just a suggestion.