diff --git a/configs/stable-diffusion/txt2img-1p4B-multinode-clip-encoder.yaml b/configs/stable-diffusion/txt2img-1p4B-multinode-clip-encoder.yaml new file mode 100644 index 0000000..ad71688 --- /dev/null +++ b/configs/stable-diffusion/txt2img-1p4B-multinode-clip-encoder.yaml @@ -0,0 +1,125 @@ +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: 32 + 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: 32 + in_channels: 4 + out_channels: 4 + model_channels: 320 + attention_resolutions: [ 4, 2, 1 ] + num_res_blocks: 2 + channel_mult: [ 1, 2, 4, 4 ] + 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 + ckpt_path: "models/first_stage_models/kl-f8/model.ckpt" + 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: + target: ldm.data.laion.WebDataModuleFromConfig + params: + tar_base: "pipe:aws s3 cp s3://s-datasets/laion5b/laion2B-data/" + batch_size: 12 + num_workers: 4 + train: + shards: '{000000..231317}.tar -' + shuffle: 10000 + image_key: jpg + image_transforms: + - target: torchvision.transforms.Resize + params: + size: 256 + interpolation: 3 + - target: torchvision.transforms.RandomCrop + params: + size: 256 + + # NOTE use enough shards to avoid empty validation loops in workers + validation: + shards: '{231318..231349}.tar -' + shuffle: 0 + image_key: jpg + image_transforms: + - target: torchvision.transforms.Resize + params: + size: 256 + interpolation: 3 + - target: torchvision.transforms.CenterCrop + params: + size: 256 + + +lightning: + callbacks: + image_logger: + target: main.ImageLogger + params: + batch_frequency: 5000 + max_images: 8 + increase_log_steps: False + log_first_step: False + + + trainer: + #replace_sampler_ddp: False + benchmark: True + val_check_interval: 50000 + num_sanity_val_steps: 0 + + + diff --git a/configs/stable-diffusion/txt2img-1p4B-multinode-t5-encoder.yaml b/configs/stable-diffusion/txt2img-1p4B-multinode-t5-encoder.yaml new file mode 100644 index 0000000..c3ff6c9 --- /dev/null +++ b/configs/stable-diffusion/txt2img-1p4B-multinode-t5-encoder.yaml @@ -0,0 +1,127 @@ +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: 32 + 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: 32 + in_channels: 4 + out_channels: 4 + model_channels: 320 + attention_resolutions: [ 4, 2, 1 ] + num_res_blocks: 2 + channel_mult: [ 1, 2, 4, 4 ] + 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 + ckpt_path: "models/first_stage_models/kl-f8/model.ckpt" + 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.FrozenT5Embedder + params: + version: "google/t5-v1_1-xl" + + +data: + target: ldm.data.laion.WebDataModuleFromConfig + params: + tar_base: "pipe:aws s3 cp s3://s-datasets/laion5b/laion2B-data/" + batch_size: 12 + num_workers: 4 + train: + shards: '{000000..231317}.tar -' + shuffle: 10000 + image_key: jpg + image_transforms: + - target: torchvision.transforms.Resize + params: + size: 256 + interpolation: 3 + - target: torchvision.transforms.RandomCrop + params: + size: 256 + + # NOTE use enough shards to avoid empty validation loops in workers + validation: + shards: '{231318..231349}.tar -' + shuffle: 0 + image_key: jpg + image_transforms: + - target: torchvision.transforms.Resize + params: + size: 256 + interpolation: 3 + - target: torchvision.transforms.CenterCrop + params: + size: 256 + + +lightning: + callbacks: + image_logger: + target: main.ImageLogger + params: + batch_frequency: 5000 + max_images: 8 + increase_log_steps: False + log_first_step: False + + + trainer: + #replace_sampler_ddp: False + benchmark: True + val_check_interval: 50000 + num_sanity_val_steps: 0 + + +