[预训练模型]173万 384WF高参DF-UDT预训练模型
本帖最后由 風水先生 于 2025-4-30 09:30 编辑纯粹用爱发电，造福坛友
预训练内容是21W张高清精选自然脸（这很重要），高参高分，是大显存显卡平衡速度和性能的最佳参数之一。
便宜不代表没好货，只是我有更好的预训练模型了~:lol
现在更新为更好的173W迭代的模型，当然价格就不会有那么优惠了~
================== Model Summary ===================
== ==
== Model name: HDzill25 SAEHD_SAEHD ==
== ==
== Current iteration: 1734827 ==
== ==
==---------------- Model Options -----------------==
== ==
== resolution: 384 ==
== face_type: wf ==
== models_opt_on_gpu: True ==
== archi: df-udt ==
== ae_dims: 384 ==
== e_dims: 96 ==
== d_dims: 96 ==
== d_mask_dims: 32 ==
== 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: False ==
== pretrain: False ==
== autobackup_hour: 6 ==
== write_preview_history: False ==
== target_iter: 0 ==
== random_src_flip: False ==
== random_dst_flip: True ==
== batch_size: 8 ==
== gan_power: 0.0 ==
== gan_patch_size: 48 ==
== gan_dims: 16 ==
== ==
==------------------ Running On ------------------==
== ==
== Device index: 0 ==
== Name: NVIDIA GeForce RTX 4090 ==
== VRAM: 20.85GB ==
== ==
====================================================
***本内容需购买可见***
感谢分享，试试好不好用
页:
[1]