Mark Gao issues

Repositories
Issues
Comments

Results 1 issues of


                                            Mark Gao

how to train a new ldm which can generate 512*512

how to train a new ldm which can generate 512*512? training a new autoencoder is needed? config.yaml as follow: model: base_learning_rate: 2.0e-06 target: ldm.models.diffusion.ddpm.LatentDiffusion params: linear_start: 0.0015 linear_end: 0.0195 num_timesteps_cond:...