tencent-ailab / IP-Adapter

The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.
Apache License 2.0
4.46k stars 289 forks source link

have no 'pytorch_model.bin' been saved during training #375

Closed xiaowu-1998 closed 1 month ago

xiaowu-1998 commented 1 month ago

when training is completed, there is no pytorch_model.bin left, and model.safetensors had only saved unet weights , so it occurs error during loading. what can I do for save image_proj and adapter_modules successfully? or loading successfully. Thanks

fhshen2022 commented 2 weeks ago

Have you solve it? I met the same issue.