SDXL
NlxlMix
- 上傳時間
- 2025年4月26日 下午6:22
- 使用數
- 411
- 評論
- 暫無評論
- 取樣步數
28
- 取樣方式
Euler a
- CFG Scale
5
- 負面
worst quality, low quality, bad anatomy, bad hands, bad feet, extra digit, fewer digits, lowres, matsunaga kouyou, takafumi
- 許可權
- 允許圖片生成與分享
- 允許使用者下載此模型
- 允許生成圖片用於商業用途
SDXL
28
Euler a
5
worst quality, low quality, bad anatomy, bad hands, bad feet, extra digit, fewer digits, lowres, matsunaga kouyou, takafumi
NlxlMix v0.5 is a merge of 4 models.Noob 1.1 Eps | Illustrious 2.0 | Rouwei v0.7 Eps | Wai-NSFW v13This merged model started with the idea of leveraging Noob's excellent dataset, Illustrious's low artificial data expressiveness, Rouwei's decent quality and artist implementation ability, and Wai's details. It was created using the Block merge method with the following recipe:( Noob + Ilxl ) + ( Rouwei + Wai-NSFW ) = NlxlMix v0.5StrengthExcellent artists reflectionIn a personal test, I tested the reflection of the drawing styles of a total of 3999 artists from pages 1 to 200 of the Danturu artists tag.While merging is not magic, surprisingly, the artists reflection itself boasted the most similar expressiveness to existing artists among the five merging models.Improved Natural Language Prompt RecognitionA disadvantage of models trained with booru tags is their relatively low natural language recognition rate.Because of this, there are cases where even basic natural language prompt cannot be implemented, but recognition has been improved through merging.More Hand-Drawn StyleBy utilizing Illustrious' Clip in the merging process, the basic drawing style present in WAI has been removed, allowing for the creation of more natural-looking drawings.WeaknessCompared to WAI | Rouwei, lacking detailSince it aims for a hand-drawn feel, the detailed intricacies, which are advantages of the three models mentioned, are somewhat lacking.More difficult to use compared to WAIIt is not easy to produce quality images without basic artist combinations.It is highly recommended to find and use artist combinations like using NAI v3.Recommended settingsPositive: It is best to use it with natural language based on the Booru tags, and it is strongly recommended to use the artist tag.Negative: worst quality, low quality, bad anatomy, bad hands, bad feet, extra digit, fewer digits, watermark as default, add low quality artists. Example) worst quality, low quality, bad anatomy, bad hands, bad feet, extra digit, fewer digits, watermark, chihuri, bb (baalbuddy), iesupaCFG: Recommended value is 5Sampler: Euler aResolution: 1024x1024 | SDXL resolutionsSteps: 28