DF_416_wf_迭代250w,高质量模型
某论坛购买后转过来的,感觉效果挺好的,出图质量也不错dfl mve分支训练的,也可以用于原版
== Model name: 416_SAEHD ==
== ==
== Current iteration: 2479935 ==
== ==
==---------------- Model Options ----------------==
== ==
== resolution: 416 ==
== face_type: wf ==
== models_opt_on_gpu: True ==
== archi: df-udt ==
== ae_dims: 320 ==
== e_dims: 80 ==
== d_dims: 80 ==
== d_mask_dims: 26 ==
== masked_training: True ==
== eyes_mouth_prio: False ==
== uniform_yaw: False ==
== blur_out_mask: False ==
== adabelief: True ==
== lr_dropout: n ==
== random_warp: True ==
== random_hsv_power: 0.0 ==
== true_face_power: 0.0 ==
== face_style_power: 0.0 ==
== bg_style_power: 0.0 ==
== ct_mode: none ==
== clipgrad: True ==
== pretrain: False ==
== autobackup_hour: 0 ==
== write_preview_history: False ==
== target_iter: 0 ==
== random_src_flip: False ==
== random_dst_flip: False ==
== batch_size: 4 ==
== gan_power: 0.0 ==
== gan_patch_size: 60 ==
== gan_dims: 20 ==
== use_fp16: False ==
== mouth_prio: False ==
== loss_function: SSIM ==
== random_downsample: False ==
== random_noise: False ==
== random_blur: False ==
== random_jpeg: False ==
== background_power: 0.0 ==
== random_color: False ==
== cpu_cap: 2 ==
== preview_samples: 1 ==
== force_full_preview: False ==
== lr: 5e-05 ==
== session_name: 默认 ==
== maximum_n_backups: 0 ==
== retraining_samples: True ==
== gan_smoothing: 0.1 ==
== gan_noise: 0.0 ==
***本内容需购买可见***
哇哦1看起来相当不错 看起来 很好,效果应该可以吧 感谢分享,这个416我笔记本4080能带动吗 bs调小,应该可以 非常感谢 这是包哥那个416吗? 签到攒零食,,哦 谢谢分享 这是包子的那个416吗?