This is a SDXL based fine-tuned merge model.VAE is included in the model (VAE selection NONE or Auto Auto).Please don't use SD1.5 VAE (it will generate noise image).If you find that the model does not switch, please update webui to version 1.6.No need to fix face for half body and close-upThis model has special training for traditional costumes.It is also very good at depicting details and colours.Thanks to SDXL's superior understanding of natural language.It is highly recommended that you use natural language to write your cues.And please forget <s>masterpiece</s> and <s>best quality</s>.You can even leave out the negative words.Suggested samplers: DPM++ 2M Karras (I use it most often), Restart (my fingers don't crumble as easily).Step count suggestion: 20+CFG recommendation: 3-11Size suggestion (official SDXL suggestion):1024×1024 (1:1) Vertical version640×1536 (9:21)768×1344 (9:16)832×1216 (2:3)896×1152 (4:5)For full body images or images with a small head, it is recommended to use the ADetailer plugin to fix the face.

Linger XL 骊歌 SDXL

lingerXLSDXL_v20.safetensors

v2.0

Linger XL (SDXL realistic large model)

This is a model based on SDXL fine-tuning and fusion of real system models.The model already includes VAE (VAE choose NONE or Auto)Please do not use VAE from SD1.5 (it will generate noisy images)If you find that the model cannot be switched, please update the webui to version 1.6 V2.0Improved image qualityEnhanced texture of characters' skinFixed teethNo need to retouch the face for half-body and close-up shots

Files with SHA256: ab0415bed53220a69765e564b46aea7efb57d10ee98ed01e35b4bb38d5280755