Nova Orange XL
Nova Orange XL is anime checkpoint with detailed skin and depth
Paying respects to WarriorMama777's OrangeMixes
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
CFG Scale: 3-5
Clip Skip: 1-2
Denoising Strength: 0.4 - 0.6
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, simple background, conjoined, bad ai-generated
Description
Apply Noob1.1 structures
FAQ
Comments (13)
planing to update novaanime?
Monthly, Yes
If I output an original character, split it into frames using manga production software, add dialogues and onomatopoeia, and make it into a manga, is that within the scope of processing that can be used for commercial purposes?
Is this within the scope of processing that can be used for commercial purposes?
Yes
@Crody Thank you for your reply. I would like to use it to create my own original manga.
v3.0 is best checkpoint ever!!broooo!!
v3 is an impressively versatile model. Try prompting it without any 'masterpiece' type prefix/suffix, and without a negative prompt. It's quite intelligent, and can do a lot more than waifus. Thank you for your work on this Crody! I've tested quite a few illustrious models recently, and for my use case, this is definitely one of the best.
no waifu no laifu tho
このモデルでアップスケールすると何故か目が小さくなって離れちゃうんだよな、なんか設定し忘れてる項目あるんかな
this model is perfect, better than other model
I really like the consistency and the creativity of this model. I just wished the art styles tags could still be used without forcing them too much with multipliers. The innate style of this model at times eats up the art style tag. But that is just a personal issue of mine, besides that, this model posing and sceneries are amazing. Having fun trying old prompts into this model.
Hopefully the character database can be updated too, it has huge database already, but its missing recent popular characters and series. Still, a great model nonetheless!