If you want to use more my checkpoint online generation, please visit here.
https://tensor.art/u/762555264535746522
V-pred-04
Data balancing and adjustment have been made, and some background logic has been optimized
Recommended settings:
Steps: 30
CFG scale: 5-7
Sampler: Euler a
Positive Prompt
,masterpiece,best quality,newest,absurdres,highres,very awa, Negative Prompt
low quality,worst quality,normal quality,text,jpeg artifacts,bad anatomy,old,early,copyright name,watermark,artist name,signature,V-pred-02
The stability of the limbs, with the overall color leaning towards a warmer tone.
v-prediction versions are experimental models.
You need to use the webui that support v-prediction.
ComfyUI
reForge
Forge
AUTOMATIC1111 (dev branch)
Use Hires. fix (The situations where ADetailer is needed are not many)
Style and Character reference NOOB
All example images are generated at 1024x1360,and Hires upscale: 1.5, Hires steps: 20, Hires upscaler: R-ESRGAN 4x+ Anime6B,Denoising strength: 0.5.
Recommended settings:
Steps: 30
CFG scale: 5-7
Sampler: Euler a
Positive Prompt
,masterpiece,best quality,newest,absurdres,highres,very awa, Negative Prompt
low quality,worst quality,normal quality,text,signature,jpeg artifacts,bad anatomy,old,early,copyright name,watermark,artist name,signature,V-pred-01
BASE:NOOB V-pred 1.0
This is a test model, attempting to use some unconventional methods to achieve merging.
The merging materials used are not purely from the v-prediction model, so there may be issues that I'm unaware of. If there are any, please leave me a message.
v-prediction versions are experimental models.
You need to use the webui that support v-prediction.
ComfyUI
reForge
Forge
AUTOMATIC1111 (dev branch)
Use Hires. fix (The situations where ADetailer is needed are not many)
Style and Character reference NOOB
All example images are generated at 1024x1360,and Hires upscale: 1.5, Hires steps: 20, Hires upscaler: R-ESRGAN 4x+ Anime6B,Denoising strength: 0.5.
Recommended settings:
Steps: 30
CFG scale: 7
Sampler: Euler a
Positive Prompt
,masterpiece,best quality,newest,absurdres,highres,very awa, Negative Prompt
low quality,worst quality,normal quality,text,signature,jpeg artifacts,bad anatomy,old,early,copyright name,watermark,artist name,signature,V2
BASE:NOOB eps 1.1
Try to ensure image quality without using quality keywords, in order to create a model that can be easily used by beginners.
Not very necessary to use Positive and Negative quality Prompt
Use Hires. fix (The situations where ADetailer is needed are not many)
Style and Character reference NOOB
All example images are generated at 1024x1360,and Hires upscale: 1.5, Hires steps: 20, Hires upscaler: R-ESRGAN 4x+ Anime6B,Denoising strength: 0.5.
NO Positive and Negative quality TAG
Recommended settings:
Steps: 30
CFG scale: 5.5
Sampler: Euler a
v1
Recommended settings:
Steps: 28-35
CFG scale: 5-7
Sampler: Euler a
Positive Prompt
,masterpiece,best quality,newest,Negative Prompt
low quality,worst quality,normal quality,text,signature,jpeg artifacts,bad anatomy,old,early,copyright name,watermark,artist name,signature,Description
FAQ
Comments (7)
Really great, knows many things, but the shading style seems hardbaked in and is really annoying when replicating other artstyles. It can do the proportions flawlessly but the outlines are always too thick and the shading is so shiny and bold which looks awful at times.
Hi! I’m planning to use this model for a commercial project, so I want to make sure I’m following the correct license.
This checkpoint appears to be derived from NoobAI-XL, which (from what I’ve seen) may include a commercial-use prohibition, but I’m not sure whether:
I should follow the NoobAI License (upstream/base model), or
the license listed on this model page (checkpoint-specific).
Could someone confirm:
Is commercial use of generated images allowed or not?
If not allowed, does that mean “no selling outputs,” or just “no selling the model/derivatives”?
Are there any requirements like attribution or share-alike for derivatives/merges?
Any clarification from the author or someone familiar with this licensing would be super helpful. Thank you!
Note: I am not a lawyer. From NoobAI hugging face: "This model's license inherits from https://huggingface.co/OnomaAIResearch/Illustrious-xl-early-release-v0 fair-ai-public-license-1.0-sd and adds the following terms. Any use of this model and its variants is bound by this license." Also on their huggingface, "We prohibit any form of commercialization, including but not limited to monetization or commercial use of the model, derivative models, or model-generated products." Almost certainly this means you cannot commercially use generated images. If this page has a license that is less restrictive, it is incorrect.
Edit: This models license is NoobAI license lol
Thanks a lot for the detailed explanation (and for the links) — that helps a ton.
Understood: since NoobAI explicitly prohibits commercialization including model-generated products, it’s safest to assume commercial use of outputs is not permitted, even if this page shows something less restrictive. I’ll proceed on a non-commercial basis and choose a different model for commercial work.
https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENSE.md
This is Stability AI CreativeML Open RAIL++-M License, All SDXL v1.0 and finetunes/loras inherit it. This license explicitly permits commercial use of the output and while it allow to give additional terms in separate license, it's debatable can they prohibit it. Also it is not enforceable any way by current law. And actually meaningless writings on the wall~
(also by some gov. agencies statements output of models is public domain and can't be subject of regulation of such licenses at all)
Very interesting U-Net on this one.
Seems to work better with ComfyUI parser than other WAI versions so far.
Interestingly lowering SelfAttention value and raising the output fixes fingers and toes.
This is completely the opposite from WAI-Illustrious and WAI-epred (and many other Noob/Illustrious model), which often require raising query and lowering key.
Idk if at its core, this is a bad thing or a good thing.
But so far, it feels pretty good (after about a week of usage). 🦄
最近在測試Anima 模型，可以沿用NOOB AI的素材和TAG也有很好的訓練及出圖效果，而且多人方面控制更好
未知作者會不會考慮試試也出一個Anima 版本