start quality prompts
masterpiece, best quality, amazing quality, very aesthetic, newest, general, negative prompts
lowres, (bad), text, error, fewer, extra, missing, worst quality, jpeg artifacts, low quality, watermark, unfinished, displeasing, oldest, early, chromatic aberration, signature, extra digits, artistic error, username, scan, [abstract], multiple views, censored, bar censor, mosaic censoring, red pupils, colored inner hair, N13NAillous-xl
This is a merged model based on NTRMIX XIII.
Unlike models based on NoobAI, this one naturally produces a beautiful default art style even without using artist prompts.
Of course, artist prompts can still be used, but they seem to have slightly less impact compared to NoobAI-based models.
The number in the model name is "XIII" converted to Arabic numerals. However, the version number of the previous model should have been "4," but adding a zero to make it decimal-based seems to have caused some confusion.
N40NAillousV2-xl
This model was created starting from the idea of using NoobAI vPred 0.6 for merging.
When merging the vPred model with the epsilonPred model, the resulting images didn't turn out as expected. However, by adjusting the block weight values, I managed to retain the TE (Text Encoder) of the vPred model while introducing some noise to create a slightly altered version. Then, I incorporated this modified model into the existing N40NAillous.
The performance doesn't feel like a massive improvement, but the images seem to come out better overall—just a subjective impression, perhaps?
While at it, I also used the newly released NTRMIX4.0 LoRA and arcain-2411 LoRA. Starting from the NoobAI 1.0 model, I redid the entire merging process from scratch, incorporating the vPred model into a newly created merged model instead of the previous N40NAillous.
used LoRA
https://civarchive.com/models/960071/better-ntrmix-lora
https://huggingface.co/Bedovyy/arcain
The above sentence was translated using ChatGPT.
N40NAillous-xl
This is a model that incorporates elements from a personal merged model to reduce the skin gloss of NTRMIX4.0.
I took "NA" from the name of the personal merged model, NoobArcaillous, and "N40" from NTRMIX4.0, and combined them.
The personal merged model is a combination of NoobAI-XL 1.0 and Lora, with an additional merge of Arcaillous-XL.
The above sentence was translated using ChatGPT.
Description
FAQ
Comments (12)
What's the difference between it and
NNGMIX-XL?
The NNGMIX model was merged based on the NoobAI model, while the NNAillous model was merged based on the NTRMIX model.
@nyangyu I wonder if there are any special advantages to them?
like Lora's perception?
@daskmaster NNGMIX works better with artist prompt combinations, allowing for higher-quality results, and it has good compatibility with LoRAs.
On the other hand, NNAillous has an excellent default art style but may struggle to maintain its full style when using artist prompts.
Ultimately, you can choose whichever suits your preferences.
@nyangyu Does that mean NNAillous is worse at supporting lora?
@daskmaster Yes, when using character LoRAs based on the Illustrious model, the results may differ from the creator's original intent. However, this doesn’t mean they cannot be used—if the results align with your preferences, feel free to use them as they are.
I have never known how to use the checkpoints in Civitai. Could you explain it to me briefly? I would greatly appreciate it.
The N13NAilous-xl model does not yet support image generation on Civitai. If your computer meets the requirements, you can download the model and use it directly, or you’ll need to wait until the model becomes available for image generation on Civitai.
Alternatively, the two N40NAilous models are supported on Civitai, so please consider using those instead.
click create icon top right of site
top left should be "model" underneath workflow, click swap
if you want to use loras that would be additional resources right under the model.
Not all models are available tho.
Could you reprint this on tensor.art?
Follows command well, understand different concept well and to top it off nice style.
Will we have a new version soon?