
Wa, a very awa LoCon extract of a NoobAI XL finetune.
Trained on NoobXL 0.65S vpred, but compatible with other Illustrious/NoobAI-XL based mixes.
The finetuned model was trained using a select number of artists. The motivation behind this is to improve the aesthetics of the noob series of models, specifically on the anatomy and manga side of it.
I started training the noob model because I found that the style of some of my preferred artists could not be well replicated and the finetune kinda evolved from there. As of now, the dataset includes high-quality work from a total of 8 artists, and more might be added in the future.
Examples (no artist tags)
Changelog:
-
v7.1 - NoobAI XL 0.65S vpred
描述:
Trained on NoobAI-XL 0.65S vpred
-
431 manually selected and cropped images
-
EVA2 tagger
-
12GB VRAM config
Artists:
-
dam
-
nonco
-
michiking
-
jp06
-
ootomo takuji
-
try (lsc)
-
nutsbutty
-
greatodoggo
训练词语:
名称: dreambooth_finetune_config.zip
大小 (KB): 1
类型: Training Data
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
名称: wa_noob_7_1.safetensors
大小 (KB): 456607
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success