"Luan Fanghua" is based on a fusion of <a target="_blank" rel="ugc" href="https://civarchive.com/models/139562?modelVersionId=344487">RealVisXL_V4.0</a> and <a target="_blank" rel="ugc" href="https://civarchive.com/models/125634?modelVersionId=471038">RongHua4.5 (1%)</a>, followed by multiple rounds of training over two months using a carefully selected dataset.All tags in the "Luan Fanghua" dataset come from GPT-4-o and the <a target="_blank" rel="ugc" href="https://huggingface.co/F16/florence2-large-ft-gufeng_v3">F16/florence2-large-ft-gufeng_v3 · Hugging Face </a> model fine-tuned by me on Hugging Face.If you are interested in fine-tuning Florence2, you can refer to the Florence2 fine-tuning script I wrote: <a target="_new" rel="ugc" href="https://github.com/facok/florence2-ft-simple">facok/florence2-ft-simple: finetune your florence2 model easy (</a><a target="_blank" rel="ugc" href="http://github.com">github.com</a><a target="_new" rel="ugc" href="https://github.com/facok/florence2-ft-simple">)</a>.乱芳华基于 <a target="_blank" rel="ugc" href="https://civarchive.com/models/139562?modelVersionId=344487">RealVisXL_V4.0</a> 和 <a target="_blank" rel="ugc" href="https://civarchive.com/models/125634?modelVersionId=471038">RongHua4.5 (1%)</a>的融合，然后在两个月时间内以精选训练集进行了多轮的训练。乱芳华训练集的所有tag来自GPT4-o和由我微调的 <a target="_blank" rel="ugc" href="https://huggingface.co/F16/florence2-large-ft-gufeng_v3">F16/florence2-large-ft-gufeng_v3 · Hugging Face 模型</a>如果你对微调Florence2有兴趣，可以参考我写的Florence2微调脚本<a target="_blank" rel="ugc" href="https://github.com/facok/florence2-ft-simple">facok/florence2-ft-simple: finetune your florence2 model easy (</a><a target="_blank" rel="ugc" href="http://github.com">github.com</a><a target="_blank" rel="ugc" href="https://github.com/facok/florence2-ft-simple">)</a>

Files with SHA256: f3335d71b24c85b062a9d14041d41662163d2b63f128b4c2e08bcbfa972004e9