![Luxlo [flux] v1版本v1.0 (ID: 811410)](https://image.1111down.com/xG1nkqKTMzGDvpLrqFT7WA/c73e8cdd-f861-450a-9722-bfb44ebc95d2/width=450/28001329.jpeg)
Trained locally using sd_scripts @ 512x512 resolution for 2000 steps. 25 image dataset trained for 80 epochs using Joycap for captions. Trained the T5XXL Text encoder as well as CLIP-L. Works best for me using the euler beta sampler in ComfyUI @ 0.8 strength with 2.7 - 3 Flux guidance.
https://instagram.com/luxlocosplay
https://www.patreon.com/luxlocosplay
https://twitter.com/luxlocosplay
描述:
512x512, AdamW optimizer. Trained using both CLIP-L and T5XXL + full nlp captions.
训练词语:
名称: luxlo_512_t5xxl_v1_flux.safetensors
大小 (KB): 149697
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
![Luxlo [flux] v1](https://image.1111down.com/xG1nkqKTMzGDvpLrqFT7WA/c78323b2-c683-4bc8-9308-c4b249b356b2/width=450/28001332.jpeg)
![Luxlo [flux] v1](https://image.1111down.com/xG1nkqKTMzGDvpLrqFT7WA/2bc9802b-847c-48ee-a2b6-64cb3cbcfadf/width=450/28001331.jpeg)
![Luxlo [flux] v1](https://image.1111down.com/xG1nkqKTMzGDvpLrqFT7WA/37c1ac6c-451a-4eeb-8ecb-dcd103ab1057/width=450/28001327.jpeg)
原文链接：https://1111down.com/1118002.html，转载请注明出处
