From 80454667da47a53e23e6e2c204a7fece83716d00 Mon Sep 17 00:00:00 2001 From: Robin Rombach Date: Thu, 28 Jul 2022 00:10:22 +0200 Subject: [PATCH] configs --- ...painting-laion-aesthetic-larger-masks.yaml | 149 ++++++++++++ .../upscaling/upscale-v1-with-f16.yaml | 214 ++++++++++++++++++ 2 files changed, 363 insertions(+) create mode 100644 configs/stable-diffusion/inpainting/v1-finetune-for-inpainting-laion-aesthetic-larger-masks.yaml create mode 100644 configs/stable-diffusion/upscaling/upscale-v1-with-f16.yaml diff --git a/configs/stable-diffusion/inpainting/v1-finetune-for-inpainting-laion-aesthetic-larger-masks.yaml b/configs/stable-diffusion/inpainting/v1-finetune-for-inpainting-laion-aesthetic-larger-masks.yaml new file mode 100644 index 0000000..0f0df07 --- /dev/null +++ b/configs/stable-diffusion/inpainting/v1-finetune-for-inpainting-laion-aesthetic-larger-masks.yaml @@ -0,0 +1,149 @@ +model: + base_learning_rate: 7.5e-05 + target: ldm.models.diffusion.ddpm.LatentInpaintDiffusion + 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: hybrid # important + monitor: val/loss_simple_ema + scale_factor: 0.18215 + ckpt_path: "/fsx/stable-diffusion/stable-diffusion/checkpoints/v1pp/v1pp-flatlined-hr.ckpt" + + scheduler_config: # 10000 warmup steps + target: ldm.lr_scheduler.LambdaLinearScheduler + params: + warm_up_steps: [ 2500 ] # NOTE for resuming. use 10000 if starting from scratch + 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 # unused + in_channels: 9 # 4 data + 4 downscaled image + 1 mask + 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 + 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: "__improvedaesthetic__" + batch_size: 2 + num_workers: 4 + multinode: True + min_size: 512 + max_pwatermark: 0.8 + 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 + postprocess: + target: ldm.data.laion.AddMask + params: + mode: "512train-large" + + # 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 + postprocess: + target: ldm.data.laion.AddMask + params: + mode: "512train-large" + + +lightning: + find_unused_parameters: False + + modelcheckpoint: + params: + every_n_train_steps: 2000 + + callbacks: + image_logger: + target: main.ImageLogger + params: + disabled: False + batch_frequency: 1000 + 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: [""] + ddim_steps: 100 # todo check these out for inpainting, + ddim_eta: 1.0 # todo check these out for inpainting, + + trainer: + benchmark: True + val_check_interval: 5000000 # really sorry + num_sanity_val_steps: 0 + accumulate_grad_batches: 2 diff --git a/configs/stable-diffusion/upscaling/upscale-v1-with-f16.yaml b/configs/stable-diffusion/upscaling/upscale-v1-with-f16.yaml new file mode 100644 index 0000000..7fe5d9a --- /dev/null +++ b/configs/stable-diffusion/upscaling/upscale-v1-with-f16.yaml @@ -0,0 +1,214 @@ +model: + base_learning_rate: 5.0e-05 + target: ldm.models.diffusion.ddpm.LatentUpscaleDiffusion + params: + low_scale_key: "lr" + linear_start: 0.001 + linear_end: 0.015 + num_timesteps_cond: 1 + log_every_t: 200 + timesteps: 1000 + first_stage_key: "jpg" + cond_stage_key: "txt" + image_size: 32 + channels: 16 + cond_stage_trainable: false + conditioning_key: "hybrid-adm" + monitor: val/loss_simple_ema + scale_factor: 0.22765929 # magic number + + low_scale_config: + target: ldm.modules.encoders.modules.LowScaleEncoder + params: + scale_factor: 0.18215 + linear_start: 0.00085 + linear_end: 0.0120 + timesteps: 1000 + max_noise_level: 250 + output_size: null + model_config: + target: ldm.models.autoencoder.AutoencoderKL + params: + embed_dim: 4 + monitor: val/rec_loss + ckpt_path: "/fsx/stable-diffusion/stable-diffusion/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 + + 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: + num_classes: 251 # timesteps for noise conditoining + image_size: 64 # not really needed + in_channels: 20 + out_channels: 16 + model_channels: 128 + attention_resolutions: [ 8, 4, 2 ] # -> at 32, 16, 8 + num_res_blocks: 2 + channel_mult: [ 1, 2, 4, 6, 8 ] + # -> res, ds: (64, 1), (32, 2), (16, 4), (6, 8), (4, 16) + 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: 16 + monitor: val/rec_loss + ckpt_path: "/fsx/stable-diffusion/stable-diffusion/models/first_stage_models/kl-f16/model.ckpt" + ddconfig: + double_z: True + z_channels: 16 + resolution: 256 + in_channels: 3 + out_ch: 3 + ch: 128 + ch_mult: [ 1,1,2,2,4 ] # num_down = len(ch_mult)-1 + num_res_blocks: 2 + attn_resolutions: [ 16 ] + dropout: 0.0 + lossconfig: + target: torch.nn.Identity + + cond_stage_config: + target: ldm.modules.encoders.modules.FrozenCLIPEmbedder + + +#data: # TODO: finetune here later +# target: ldm.data.laion.WebDataModuleFromConfig +# params: +# tar_base: "pipe:aws s3 cp s3://s-datasets/laion-high-resolution/" +# batch_size: 10 +# num_workers: 4 +# train: +# shards: '{00000..17279}.tar -' +# shuffle: 10000 +# image_key: jpg +# image_transforms: +# - target: torchvision.transforms.Resize +# params: +# size: 1024 +# interpolation: 3 +# - target: torchvision.transforms.RandomCrop +# params: +# size: 1024 +# postprocess: +# target: ldm.data.laion.AddLR +# params: +# factor: 2 +# +# # 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: 1024 +# interpolation: 3 +# - target: torchvision.transforms.CenterCrop +# params: +# size: 1024 +# postprocess: +# target: ldm.data.laion.AddLR +# params: +# factor: 2 + +data: + target: ldm.data.laion.WebDataModuleFromConfig + params: + tar_base: "__improvedaesthetic__" + batch_size: 28 + num_workers: 4 + multinode: True + min_size: 512 + 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 + postprocess: + target: ldm.data.laion.AddLR + params: + factor: 2 + + # 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 + postprocess: + target: ldm.data.laion.AddLR + params: + factor: 2 + + +lightning: + find_unused_parameters: False + + callbacks: + image_logger: + target: main.ImageLogger + params: + batch_frequency: 1000 + 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: + benchmark: True + val_check_interval: 5000000 # really sorry + num_sanity_val_steps: 0 + accumulate_grad_batches: 2