model: base_learning_rate: 1.0e-04 target: ldm.models.diffusion.ddpm.LatentDiffusion params: linear_start: 0.00085 linear_end: 0.0120 num_timesteps_cond: 1 log_every_t: 200 timesteps: 1000 first_stage_key: "jpg" cond_stage_key: "txt" image_size: 64 channels: 4 cond_stage_trainable: false # Note: different from the one we trained before conditioning_key: crossattn monitor: val/loss_simple_ema scale_factor: 0.18215 scheduler_config: # 10000 warmup steps target: ldm.lr_scheduler.LambdaLinearScheduler params: warm_up_steps: [ 10000 ] cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases f_start: [ 1.e-6 ] f_max: [ 1. ] f_min: [ 1. ] unet_config: target: ldm.modules.diffusionmodules.openaimodel.UNetModel params: image_size: 64 # unused in_channels: 4 out_channels: 4 model_channels: 384 attention_resolutions: [ 8, 4, 2, 1 ] num_res_blocks: [ 2, 2, 2, 2 ] channel_mult: [ 1, 2, 4, 4 ] disable_self_attentions: [ False, False, False, False ] # converts the self-attention to a cross-attention layer if true num_heads: 8 use_spatial_transformer: True transformer_depth: 1 context_dim: 768 use_checkpoint: True legacy: False first_stage_config: target: ldm.models.autoencoder.AutoencoderKL params: embed_dim: 4 monitor: val/rec_loss ddconfig: double_z: true z_channels: 4 resolution: 256 in_channels: 3 out_ch: 3 ch: 128 ch_mult: - 1 - 2 - 4 - 4 num_res_blocks: 2 attn_resolutions: [] dropout: 0.0 lossconfig: target: torch.nn.Identity cond_stage_config: target: ldm.modules.encoders.modules.FrozenCLIPEmbedder data: # TODO target: main.DataModuleFromConfig params: batch_size: 1 num_workers: 4 wrap: false train: target: ldm.data.dummy.DummyData params: length: 20000 size: [512, 512, 3] validation: target: ldm.data.dummy.DummyData params: length: 10000 size: [512, 512, 3] #data: # target: ldm.data.laion.WebDataModuleFromConfig # params: # tar_base: "pipe:aws s3 cp s3://s-datasets/laion-high-resolution/" # batch_size: 4 # num_workers: 4 # multinode: True # train: # shards: '{00000..17279}.tar -' # shuffle: 10000 # image_key: jpg # image_transforms: # - target: torchvision.transforms.Resize # params: # size: 512 # interpolation: 3 # - target: torchvision.transforms.RandomCrop # params: # size: 512 # # # NOTE use enough shards to avoid empty validation loops in workers # validation: # shards: '{17280..17535}.tar -' # shuffle: 0 # image_key: jpg # image_transforms: # - target: torchvision.transforms.Resize # params: # size: 512 # interpolation: 3 # - target: torchvision.transforms.CenterCrop # params: # size: 512 lightning: callbacks: image_logger: target: main.ImageLogger params: batch_frequency: 5 # TODO max_images: 4 increase_log_steps: False log_first_step: False log_images_kwargs: use_ema_scope: False inpaint: False plot_progressive_rows: False plot_diffusion_rows: False N: 4 unconditional_guidance_scale: 3.0 unconditional_guidance_label: [""] trainer: #replace_sampler_ddp: False benchmark: True val_check_interval: 1000 # TODO: 5000000 # really sorry num_sanity_val_steps: 0 accumulate_grad_batches: 2