[dreambooth] fixing the incompatibity in requirements.txt (#3190) (#3378)

* Update requirements.txt

* Update environment.yaml

* Update README.md

* Update environment.yaml

* Update README.md

* Update README.md

* Delete requirements_colossalai.txt

* Update requirements.txt

* Update README.md

examples/images/diffusion/configs/Teyvat/train_colossalai_teyvat.yaml

 model:
   base_learning_rate: 1.0e-4
-  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  #target: ldm.models.diffusion.ddpm.LatentDiffusion
   params:
     parameterization: "v"
     linear_start: 0.00085
@@ -20,7 +20,7 @@ model:
     use_ema: False
 
     scheduler_config: # 10000 warmup steps
-      target: ldm.lr_scheduler.LambdaLinearScheduler
+      #target: ldm.lr_scheduler.LambdaLinearScheduler
       params:
         warm_up_steps: [ 1 ] # NOTE for resuming. use 10000 if starting from scratch
         cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
@@ -30,7 +30,7 @@ model:
 
 
     unet_config:
-      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      #target: ldm.modules.diffusionmodules.openaimodel.UNetModel
       params:
         use_checkpoint: True
         use_fp16: True
@@ -49,7 +49,7 @@ model:
         legacy: False
 
     first_stage_config:
-      target: ldm.models.autoencoder.AutoencoderKL
+      #target: ldm.models.autoencoder.AutoencoderKL
       params:
         embed_dim: 4
         monitor: val/rec_loss
@@ -73,13 +73,13 @@ model:
           target: torch.nn.Identity
 
     cond_stage_config:
-      target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
+      #target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
       params:
         freeze: True
         layer: "penultimate"
 
 data:
-  target: main.DataModuleFromConfig
+  #target: main.DataModuleFromConfig
   params:
     batch_size: 16
     num_workers: 4
@@ -105,7 +105,7 @@ lightning:
     precision: 16
     auto_select_gpus: False
     strategy:
-      target: strategies.ColossalAIStrategy
+      #target: strategies.ColossalAIStrategy
       params:
         use_chunk: True
         enable_distributed_storage: True
@@ -120,7 +120,7 @@ lightning:
 
   logger_config:
     wandb:
-      target: loggers.WandbLogger
+      #target: loggers.WandbLogger
       params:
           name: nowname
           save_dir: "/tmp/diff_log/"

examples/images/diffusion/configs/train_colossalai.yaml

 model:
   base_learning_rate: 1.0e-4
-  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  #target: ldm.models.diffusion.ddpm.LatentDiffusion
   params:
     parameterization: "v"
     linear_start: 0.00085
@@ -19,7 +19,7 @@ model:
     use_ema: False # we set this to false because this is an inference only config
 
     scheduler_config: # 10000 warmup steps
-      target: ldm.lr_scheduler.LambdaLinearScheduler
+      #target: ldm.lr_scheduler.LambdaLinearScheduler
       params:
         warm_up_steps: [ 1 ] # NOTE for resuming. use 10000 if starting from scratch
         cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
@@ -29,7 +29,7 @@ model:
 
 
     unet_config:
-      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      #target: ldm.modules.diffusionmodules.openaimodel.UNetModel
       params:
         use_checkpoint: True
         use_fp16: True
@@ -48,7 +48,7 @@ model:
         legacy: False
 
     first_stage_config:
-      target: ldm.models.autoencoder.AutoencoderKL
+      #target: ldm.models.autoencoder.AutoencoderKL
       params:
         embed_dim: 4
         monitor: val/rec_loss
@@ -69,16 +69,16 @@ model:
           attn_resolutions: []
           dropout: 0.0
         lossconfig:
-          target: torch.nn.Identity
+          #target: torch.nn.Identity
 
     cond_stage_config:
-      target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
+      #target: #ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
       params:
         freeze: True
         layer: "penultimate"
 
 data:
-  target: main.DataModuleFromConfig
+  #target: #main.DataModuleFromConfig
   params:
     batch_size: 128
     wrap: False
@@ -88,20 +88,20 @@ data:
     train:
       target: ldm.data.base.Txt2ImgIterableBaseDataset
       params:
-        file_path: # YOUR DATASET_PATH
+        file_path: /data/scratch/diffuser/laion_part0/
         world_size: 1
         rank: 0
 
 lightning:
   trainer:
     accelerator: 'gpu'
-    devices: 8
+    devices: 2
     log_gpu_memory: all
     max_epochs: 2
     precision: 16
     auto_select_gpus: False
     strategy:
-      target: strategies.ColossalAIStrategy
+      #target: #strategies.ColossalAIStrategy
       params:
         use_chunk: True
         enable_distributed_storage: True
@@ -116,7 +116,7 @@ lightning:
 
   logger_config:
     wandb:
-      target: loggers.WandbLogger
+      #target: #loggers.WandbLogger
       params:
           name: nowname
           save_dir: "/tmp/diff_log/"

examples/images/diffusion/configs/train_colossalai_cifar10.yaml

 model:
   base_learning_rate: 1.0e-4
-  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  #target: ldm.models.diffusion.ddpm.LatentDiffusion
   params:
     parameterization: "v"
     linear_start: 0.00085
@@ -19,7 +19,7 @@ model:
     use_ema: False # we set this to false because this is an inference only config
 
     scheduler_config: # 10000 warmup steps
-      target: ldm.lr_scheduler.LambdaLinearScheduler
+      #target: ldm.lr_scheduler.LambdaLinearScheduler
       params:
         warm_up_steps: [ 1 ] # NOTE for resuming. use 10000 if starting from scratch
         cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
@@ -29,7 +29,7 @@ model:
 
 
     unet_config:
-      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      #target: ldm.modules.diffusionmodules.openaimodel.UNetModel
       params:
         use_checkpoint: True
         use_fp16: True
@@ -48,7 +48,7 @@ model:
         legacy: False
 
     first_stage_config:
-      target: ldm.models.autoencoder.AutoencoderKL
+      #target: ldm.models.autoencoder.AutoencoderKL
       params:
         embed_dim: 4
         monitor: val/rec_loss
@@ -69,16 +69,16 @@ model:
           attn_resolutions: []
           dropout: 0.0
         lossconfig:
-          target: torch.nn.Identity
+          #target: torch.nn.Identity
 
     cond_stage_config:
-      target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
+      #target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
       params:
         freeze: True
         layer: "penultimate"
 
 data:
-  target: main.DataModuleFromConfig
+  #target: main.DataModuleFromConfig
   params:
     batch_size: 4
     num_workers: 4
@@ -105,7 +105,7 @@ lightning:
     precision: 16
     auto_select_gpus: False
     strategy:
-      target: strategies.ColossalAIStrategy
+      #target: strategies.ColossalAIStrategy
       params:
         use_chunk: True
         enable_distributed_storage: True

examples/images/diffusion/configs/train_ddp.yaml

 model:
   base_learning_rate: 1.0e-4
-  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  #target: ldm.models.diffusion.ddpm.LatentDiffusion
   params:
     parameterization: "v"
     linear_start: 0.00085
@@ -29,7 +29,7 @@ model:
 
 
     unet_config:
-      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      #target: ldm.modules.diffusionmodules.openaimodel.UNetModel
       params:
         use_checkpoint: True
         use_fp16: True
@@ -48,7 +48,7 @@ model:
         legacy: False
 
     first_stage_config:
-      target: ldm.models.autoencoder.AutoencoderKL
+      #target: ldm.models.autoencoder.AutoencoderKL
       params:
         embed_dim: 4
         monitor: val/rec_loss
@@ -72,13 +72,13 @@ model:
           target: torch.nn.Identity
 
     cond_stage_config:
-      target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
+      #target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
       params:
         freeze: True
         layer: "penultimate"
 
 data:
-  target: main.DataModuleFromConfig
+  #target: main.DataModuleFromConfig
   params:
     batch_size: 128
     # num_workwers should be 2 * batch_size, and the total num less than 1024
@@ -100,7 +100,7 @@ lightning:
     precision: 16
     auto_select_gpus: False
     strategy:
-      target: strategies.DDPStrategy
+      #target: strategies.DDPStrategy
       params:
         find_unused_parameters: False
     log_every_n_steps: 2
@@ -111,7 +111,7 @@ lightning:
 
   logger_config:
     wandb:
-      target: loggers.WandbLogger
+      #target: loggers.WandbLogger
       params:
           name: nowname
           save_dir: "/data2/tmp/diff_log/"

examples/images/diffusion/ldm/models/autoencoder.py

@@ -6,11 +6,10 @@ except:
 
 import torch.nn.functional as F
 from contextlib import contextmanager
+from torch.nn import Identity
 
 from ldm.modules.diffusionmodules.model import Encoder, Decoder
 from ldm.modules.distributions.distributions import DiagonalGaussianDistribution
-
-from ldm.util import instantiate_from_config
 from ldm.modules.ema import LitEma
 
 
@@ -32,7 +31,7 @@ class AutoencoderKL(pl.LightningModule):
         self.image_key = image_key
         self.encoder = Encoder(**ddconfig)
         self.decoder = Decoder(**ddconfig)
-        self.loss = instantiate_from_config(lossconfig)
+        self.loss = Identity(**lossconfig.get("params", dict()))
         assert ddconfig["double_z"]
         self.quant_conv = torch.nn.Conv2d(2*ddconfig["z_channels"], 2*embed_dim, 1)
         self.post_quant_conv = torch.nn.Conv2d(embed_dim, ddconfig["z_channels"], 1)

examples/images/diffusion/ldm/models/diffusion/classifier.py

@@ -9,9 +9,10 @@ from copy import deepcopy
 from einops import rearrange
 from glob import glob
 from natsort import natsorted
-
+from ldm.models.diffusion.ddpm import LatentDiffusion
+from ldm.lr_scheduler import LambdaLinearScheduler
 from ldm.modules.diffusionmodules.openaimodel import EncoderUNetModel, UNetModel
-from ldm.util import log_txt_as_img, default, ismap, instantiate_from_config
+from ldm.util import log_txt_as_img, default, ismap
 
 __models__ = {
     'class_label': EncoderUNetModel,
@@ -86,7 +87,7 @@ class NoisyLatentImageClassifier(pl.LightningModule):
             print(f"Unexpected Keys: {unexpected}")
 
     def load_diffusion(self):
-        model = instantiate_from_config(self.diffusion_config)
+        model = LatentDiffusion(**self.diffusion_config.get('params',dict()))
         self.diffusion_model = model.eval()
         self.diffusion_model.train = disabled_train
         for param in self.diffusion_model.parameters():
@@ -221,7 +222,7 @@ class NoisyLatentImageClassifier(pl.LightningModule):
         optimizer = AdamW(self.model.parameters(), lr=self.learning_rate, weight_decay=self.weight_decay)
 
         if self.use_scheduler:
-            scheduler = instantiate_from_config(self.scheduler_config)
+            scheduler = LambdaLinearScheduler(**self.scheduler_config.get('params',dict()))
 
             print("Setting up LambdaLR scheduler...")
             scheduler = [

examples/images/diffusion/ldm/models/diffusion/ddpm.py

@@ -22,6 +22,7 @@ from contextlib import contextmanager, nullcontext
 from functools import partial
 
 from einops import rearrange, repeat
+from ldm.lr_scheduler import LambdaLinearScheduler
 from ldm.models.autoencoder import *
 from ldm.models.autoencoder import AutoencoderKL, IdentityFirstStage
 from ldm.models.diffusion.ddim import *
@@ -29,9 +30,10 @@ from ldm.models.diffusion.ddim import DDIMSampler
 from ldm.modules.diffusionmodules.model import *
 from ldm.modules.diffusionmodules.model import Decoder, Encoder, Model
 from ldm.modules.diffusionmodules.openaimodel import *
-from ldm.modules.diffusionmodules.openaimodel import AttentionPool2d
+from ldm.modules.diffusionmodules.openaimodel import AttentionPool2d, UNetModel
 from ldm.modules.diffusionmodules.util import extract_into_tensor, make_beta_schedule, noise_like
 from ldm.modules.distributions.distributions import DiagonalGaussianDistribution, normal_kl
+from ldm.modules.diffusionmodules.upscaling import ImageConcatWithNoiseAugmentation
 from ldm.modules.ema import LitEma
 from ldm.modules.encoders.modules import *
 from ldm.util import count_params, default, exists, instantiate_from_config, isimage, ismap, log_txt_as_img, mean_flat
@@ -39,6 +41,7 @@ from omegaconf import ListConfig
 from torch.optim.lr_scheduler import LambdaLR
 from torchvision.utils import make_grid
 from tqdm import tqdm
+from ldm.modules.midas.api import MiDaSInference
 
 __conditioning_keys__ = {'concat': 'c_concat', 'crossattn': 'c_crossattn', 'adm': 'y'}
 
@@ -690,7 +693,7 @@ class LatentDiffusion(DDPM):
             self.make_cond_schedule()
 
     def instantiate_first_stage(self, config):
-        model = instantiate_from_config(config)
+        model = AutoencoderKL(**config.get("params", dict()))
         self.first_stage_model = model.eval()
         self.first_stage_model.train = disabled_train
         for param in self.first_stage_model.parameters():
@@ -706,7 +709,7 @@ class LatentDiffusion(DDPM):
                 self.cond_stage_model = None
                 # self.be_unconditional = True
             else:
-                model = instantiate_from_config(config)
+                model = FrozenOpenCLIPEmbedder(**config.get("params", dict()))
                 self.cond_stage_model = model.eval()
                 self.cond_stage_model.train = disabled_train
                 for param in self.cond_stage_model.parameters():
@@ -714,7 +717,7 @@ class LatentDiffusion(DDPM):
         else:
             assert config != '__is_first_stage__'
             assert config != '__is_unconditional__'
-            model = instantiate_from_config(config)
+            model = FrozenOpenCLIPEmbedder(**config.get("params", dict()))
             self.cond_stage_model = model
 
     def _get_denoise_row_from_list(self, samples, desc='', force_no_decoder_quantization=False):
@@ -1479,8 +1482,7 @@ class LatentDiffusion(DDPM):
 
         # opt = torch.optim.AdamW(params, lr=lr)
         if self.use_scheduler:
-            assert 'target' in self.scheduler_config
-            scheduler = instantiate_from_config(self.scheduler_config)
+            scheduler = LambdaLinearScheduler(**self.scheduler_config.get("params", dict()))
 
             rank_zero_info("Setting up LambdaLR scheduler...")
             scheduler = [{'scheduler': LambdaLR(opt, lr_lambda=scheduler.schedule), 'interval': 'step', 'frequency': 1}]
@@ -1502,7 +1504,7 @@ class DiffusionWrapper(pl.LightningModule):
     def __init__(self, diff_model_config, conditioning_key):
         super().__init__()
         self.sequential_cross_attn = diff_model_config.pop("sequential_crossattn", False)
-        self.diffusion_model = instantiate_from_config(diff_model_config)
+        self.diffusion_model = UNetModel(**diff_model_config.get("params", dict()))
         self.conditioning_key = conditioning_key
         assert self.conditioning_key in [None, 'concat', 'crossattn', 'hybrid', 'adm', 'hybrid-adm', 'crossattn-adm']
 
@@ -1551,7 +1553,7 @@ class LatentUpscaleDiffusion(LatentDiffusion):
         self.noise_level_key = noise_level_key
 
     def instantiate_low_stage(self, config):
-        model = instantiate_from_config(config)
+        model = ImageConcatWithNoiseAugmentation(**config.get("params", dict()))
         self.low_scale_model = model.eval()
         self.low_scale_model.train = disabled_train
         for param in self.low_scale_model.parameters():
@@ -1933,7 +1935,7 @@ class LatentDepth2ImageDiffusion(LatentFinetuneDiffusion):
 
     def __init__(self, depth_stage_config, concat_keys=("midas_in",), *args, **kwargs):
         super().__init__(concat_keys=concat_keys, *args, **kwargs)
-        self.depth_model = instantiate_from_config(depth_stage_config)
+        self.depth_model = MiDaSInference(**depth_stage_config.get("params", dict()))
         self.depth_stage_key = concat_keys[0]
 
     @torch.no_grad()
@@ -2006,7 +2008,7 @@ class LatentUpscaleFinetuneDiffusion(LatentFinetuneDiffusion):
             self.low_scale_key = low_scale_key
 
     def instantiate_low_stage(self, config):
-        model = instantiate_from_config(config)
+        model = ImageConcatWithNoiseAugmentation(**config.get("params", dict()))
         self.low_scale_model = model.eval()
         self.low_scale_model.train = disabled_train
         for param in self.low_scale_model.parameters():

examples/images/diffusion/main.py

@@ -23,19 +23,21 @@ from packaging import version
 from PIL import Image
 from prefetch_generator import BackgroundGenerator
 from torch.utils.data import DataLoader, Dataset, Subset, random_split
-
-try:
-    from lightning.pytorch import seed_everything
-    from lightning.pytorch.callbacks import Callback, LearningRateMonitor, ModelCheckpoint
-    from lightning.pytorch.trainer import Trainer
-    from lightning.pytorch.utilities import rank_zero_info, rank_zero_only
-    LIGHTNING_PACK_NAME = "lightning.pytorch."
-except:
-    from pytorch_lightning import seed_everything
-    from pytorch_lightning.callbacks import Callback, LearningRateMonitor, ModelCheckpoint
-    from pytorch_lightning.trainer import Trainer
-    from pytorch_lightning.utilities import rank_zero_info, rank_zero_only
-    LIGHTNING_PACK_NAME = "pytorch_lightning."
+from ldm.models.diffusion.ddpm import LatentDiffusion
+#try:
+from lightning.pytorch import seed_everything
+from lightning.pytorch.callbacks import Callback, LearningRateMonitor, ModelCheckpoint
+from lightning.pytorch.trainer import Trainer
+from lightning.pytorch.utilities import rank_zero_info, rank_zero_only
+from lightning.pytorch.loggers import WandbLogger, TensorBoardLogger
+from lightning.pytorch.strategies import ColossalAIStrategy,DDPStrategy
+LIGHTNING_PACK_NAME = "lightning.pytorch."
+# #except:
+#     from pytorch_lightning import seed_everything
+#     from pytorch_lightning.callbacks import Callback, LearningRateMonitor, ModelCheckpoint
+#     from pytorch_lightning.trainer import Trainer
+#     from pytorch_lightning.utilities import rank_zero_info, rank_zero_only
+#     LIGHTNING_PACK_NAME = "pytorch_lightning."
 
 from ldm.data.base import Txt2ImgIterableBaseDataset
 from ldm.util import instantiate_from_config
@@ -575,7 +577,7 @@ if __name__ == "__main__":
     #          target: path to test dataset
     #          params:
     #              key: value
-    # lightning: (optional, has sane defaults and can be specified on cmdline)
+    # lightning: (optional, has same defaults and can be specified on cmdline)
     #   trainer:
     #       additional arguments to trainer
     #   logger:
@@ -653,7 +655,7 @@ if __name__ == "__main__":
     # Sets the seed for the random number generator to ensure reproducibility
     seed_everything(opt.seed)
 
-    # Intinalize and save configuratioon using teh OmegaConf library. 
+    # Intinalize and save configuration using the OmegaConf library. 
     try:
         # init and save configs
         configs = [OmegaConf.load(cfg) for cfg in opt.base]
@@ -687,7 +689,7 @@ if __name__ == "__main__":
             config.model["params"].update({"ckpt": ckpt})
             rank_zero_info("Using ckpt_path = {}".format(config.model["params"]["ckpt"]))
 
-        model = instantiate_from_config(config.model)
+        model = LatentDiffusion(**config.model.get("params", dict()))
         # trainer and callbacks
         trainer_kwargs = dict()
 
@@ -696,7 +698,7 @@ if __name__ == "__main__":
         # These loggers are specified as targets in the dictionary, along with the configuration settings specific to each logger.
         default_logger_cfgs = {
             "wandb": {
-                "target": LIGHTNING_PACK_NAME + "loggers.WandbLogger",
+                #"target": LIGHTNING_PACK_NAME + "loggers.WandbLogger",
                 "params": {
                     "name": nowname,
                     "save_dir": logdir,
@@ -705,7 +707,7 @@ if __name__ == "__main__":
                 }
             },
             "tensorboard": {
-                "target": LIGHTNING_PACK_NAME + "loggers.TensorBoardLogger",
+                #"target": LIGHTNING_PACK_NAME + "loggers.TensorBoardLogger",
                 "params": {
                     "save_dir": logdir,
                     "name": "diff_tb",
@@ -718,30 +720,32 @@ if __name__ == "__main__":
         default_logger_cfg = default_logger_cfgs["tensorboard"]
         if "logger" in lightning_config:
             logger_cfg = lightning_config.logger
+            logger_cfg = OmegaConf.merge(default_logger_cfg, logger_cfg)
+            trainer_kwargs["logger"] = WandbLogger(**logger_cfg.get("params", dict()))
         else:
             logger_cfg = default_logger_cfg
-        logger_cfg = OmegaConf.merge(default_logger_cfg, logger_cfg)
-        trainer_kwargs["logger"] = instantiate_from_config(logger_cfg)
+            logger_cfg = OmegaConf.merge(default_logger_cfg, logger_cfg)
+            trainer_kwargs["logger"] = TensorBoardLogger(**logger_cfg.get("params", dict()))
+        
 
         # config the strategy, defualt is ddp
         if "strategy" in trainer_config:
             strategy_cfg = trainer_config["strategy"]
-            strategy_cfg["target"] = LIGHTNING_PACK_NAME + strategy_cfg["target"]
+            trainer_kwargs["strategy"] = ColossalAIStrategy(**strategy_cfg.get("params", dict()))
         else:
             strategy_cfg = {
-                "target": LIGHTNING_PACK_NAME + "strategies.DDPStrategy",
+                #"target": LIGHTNING_PACK_NAME + "strategies.DDPStrategy",
                 "params": {
                     "find_unused_parameters": False
                 }
             }
-
-        trainer_kwargs["strategy"] = instantiate_from_config(strategy_cfg)
+            trainer_kwargs["strategy"] = DDPStrategy(**strategy_cfg.get("params", dict()))
 
         # Set up ModelCheckpoint callback to save best models
         # modelcheckpoint - use TrainResult/EvalResult(checkpoint_on=metric) to
         # specify which metric is used to determine best models
         default_modelckpt_cfg = {
-            "target": LIGHTNING_PACK_NAME + "callbacks.ModelCheckpoint",
+            #"target": LIGHTNING_PACK_NAME + "callbacks.ModelCheckpoint",
             "params": {
                 "dirpath": ckptdir,
                 "filename": "{epoch:06}",
@@ -759,13 +763,13 @@ if __name__ == "__main__":
             modelckpt_cfg = OmegaConf.create()
         modelckpt_cfg = OmegaConf.merge(default_modelckpt_cfg, modelckpt_cfg)
         if version.parse(pl.__version__) < version.parse('1.4.0'):
-            trainer_kwargs["checkpoint_callback"] = instantiate_from_config(modelckpt_cfg)
+            trainer_kwargs["checkpoint_callback"] = ModelCheckpoint(**modelckpt_cfg.get("params", dict()))
 
         # Set up various callbacks, including logging, learning rate monitoring, and CUDA management
         # add callback which sets up log directory
         default_callbacks_cfg = {
             "setup_callback": {                           # callback to set up the training
-                "target": "main.SetupCallback",
+                #"target": "main.SetupCallback",
                 "params": {
                     "resume": opt.resume,                 # resume training if applicable
                     "now": now, 
@@ -777,7 +781,7 @@ if __name__ == "__main__":
                 }
             },
             "image_logger": {                             # callback to log image data
-                "target": "main.ImageLogger",
+                #"target": "main.ImageLogger",
                 "params": {
                     "batch_frequency": 750,               # how frequently to log images
                     "max_images": 4,                      # maximum number of images to log
@@ -785,14 +789,14 @@ if __name__ == "__main__":
                 }
             },
             "learning_rate_logger": {                     # callback to log learning rate
-                "target": "main.LearningRateMonitor",
+                #"target": "main.LearningRateMonitor",
                 "params": {
                     "logging_interval": "step",           # logging frequency (either 'step' or 'epoch')
         # "log_momentum": True                            # whether to log momentum (currently commented out)
                 }
             },
             "cuda_callback": {                            # callback to handle CUDA-related operations
-                "target": "main.CUDACallback"
+                #"target": "main.CUDACallback"
             },
         }
 
@@ -810,7 +814,7 @@ if __name__ == "__main__":
                 'Caution: Saving checkpoints every n train steps without deleting. This might require some free space.')
             default_metrics_over_trainsteps_ckpt_dict = {
                 'metrics_over_trainsteps_checkpoint': {
-                    "target": LIGHTNING_PACK_NAME + 'callbacks.ModelCheckpoint',
+                    #"target": LIGHTNING_PACK_NAME + 'callbacks.ModelCheckpoint',
                     'params': {
                         "dirpath": os.path.join(ckptdir, 'trainstep_checkpoints'),
                         "filename": "{epoch:06}-{step:09}",
@@ -825,15 +829,35 @@ if __name__ == "__main__":
         
         # Merge the default callbacks configuration with the specified callbacks configuration, and instantiate the callbacks
         callbacks_cfg = OmegaConf.merge(default_callbacks_cfg, callbacks_cfg)
+        
+        #Instantiate items according to the configs
+        trainer_kwargs.setdefault("callbacks", [])
 
-        trainer_kwargs["callbacks"] = [instantiate_from_config(callbacks_cfg[k]) for k in callbacks_cfg]
+        if "setup_callback" in callbacks_cfg:
+            setup_callback_config = callbacks_cfg["setup_callback"]
+            trainer_kwargs["callbacks"].append(SetupCallback(**setup_callback_config.get("params", dict())))
 
-        # Create a Trainer object with the specified command-line arguments and keyword arguments, and set the log directory
+        if "image_logger" in callbacks_cfg:
+            image_logger_config = callbacks_cfg["image_logger"]
+            trainer_kwargs["callbacks"].append(ImageLogger(**image_logger_config.get("params", dict())))
+
+        if "learning_rate_logger" in callbacks_cfg:
+            learning_rate_logger_config = callbacks_cfg["learning_rate_logger"]
+            trainer_kwargs["callbacks"].append(LearningRateMonitor(**learning_rate_logger_config.get("params", dict())))
+
+        if "cuda_callback" in callbacks_cfg:
+            cuda_callback_config = callbacks_cfg["cuda_callback"]
+            trainer_kwargs["callbacks"].append(CUDACallback(**cuda_callback_config.get("params", dict())))
+
+        if "metrics_over_trainsteps_checkpoint" in callbacks_cfg:
+            metrics_over_config = callbacks_cfg['metrics_over_trainsteps_checkpoint']
+            trainer_kwargs["callbacks"].append(ModelCheckpoint(**metrics_over_config.get("params", dict())))
+        #trainer_kwargs["callbacks"] = [instantiate_from_config(callbacks_cfg[k]) for k in callbacks_cfg]
         trainer = Trainer.from_argparse_args(trainer_opt, **trainer_kwargs)
         trainer.logdir = logdir
-
+        
         # Create a data module based on the configuration file
-        data = instantiate_from_config(config.data)
+        data = DataModuleFromConfig(**config.data.get("params", dict()))
         # NOTE according to https://pytorch-lightning.readthedocs.io/en/latest/datamodules.html
         # calling these ourselves should not be necessary but it is.
         # lightning still takes care of proper multiprocessing though

examples/images/diffusion/scripts/img2img.py

@@ -20,8 +20,8 @@ from imwatermark import WatermarkEncoder
 
 
 from scripts.txt2img import put_watermark
-from ldm.util import instantiate_from_config
 from ldm.models.diffusion.ddim import DDIMSampler
+from ldm.models.diffusion.ddpm import LatentDiffusion
 from utils import replace_module, getModelSize
 
 
@@ -36,7 +36,7 @@ def load_model_from_config(config, ckpt, verbose=False):
     if "global_step" in pl_sd:
         print(f"Global Step: {pl_sd['global_step']}")
     sd = pl_sd["state_dict"]
-    model = instantiate_from_config(config.model)
+    model = LatentDiffusion(**config.model.get("params", dict()))
     m, u = model.load_state_dict(sd, strict=False)
     if len(m) > 0 and verbose:
         print("missing keys:")

examples/images/diffusion/scripts/inpaint.py

@@ -4,7 +4,7 @@ from PIL import Image
 from tqdm import tqdm
 import numpy as np
 import torch
-from main import instantiate_from_config
+from ldm.models.diffusion.ddpm import LatentgDiffusion
 from ldm.models.diffusion.ddim import DDIMSampler
 
 
@@ -57,7 +57,7 @@ if __name__ == "__main__":
     print(f"Found {len(masks)} inputs.")
 
     config = OmegaConf.load("models/ldm/inpainting_big/config.yaml")
-    model = instantiate_from_config(config.model)
+    model = LatentDiffusion(**config.model.get("params", dict()))
     model.load_state_dict(torch.load("models/ldm/inpainting_big/last.ckpt")["state_dict"],
                           strict=False)
 

examples/images/diffusion/scripts/knn2img.py

@@ -13,9 +13,10 @@ import scann
 import time
 from multiprocessing import cpu_count
 
-from ldm.util import instantiate_from_config, parallel_data_prefetch
+from ldm.util import parallel_data_prefetch
 from ldm.models.diffusion.ddim import DDIMSampler
 from ldm.models.diffusion.plms import PLMSSampler
+from ldm.models.diffusion.ddpm import LatentDiffusion
 from ldm.modules.encoders.modules import FrozenClipImageEmbedder, FrozenCLIPTextEmbedder
 
 DATABASES = [
@@ -44,7 +45,7 @@ def load_model_from_config(config, ckpt, verbose=False):
     if "global_step" in pl_sd:
         print(f"Global Step: {pl_sd['global_step']}")
     sd = pl_sd["state_dict"]
-    model = instantiate_from_config(config.model)
+    model = LatentDiffusion(**config.model.get("params", dict()))
     m, u = model.load_state_dict(sd, strict=False)
     if len(m) > 0 and verbose:
         print("missing keys:")

examples/images/diffusion/scripts/sample_diffusion.py

@@ -8,7 +8,6 @@ from omegaconf import OmegaConf
 from PIL import Image
 
 from ldm.models.diffusion.ddim import DDIMSampler
-from ldm.util import instantiate_from_config
 
 rescale = lambda x: (x + 1.) / 2.
 
@@ -218,7 +217,7 @@ def get_parser():
 
 
 def load_model_from_config(config, sd):
-    model = instantiate_from_config(config)
+    model = LatentDiffusion(**config.get("params", dict()))
     model.load_state_dict(sd,strict=False)
     model.cuda()
     model.eval()

examples/images/diffusion/scripts/tests/test_checkpoint.py

@@ -9,7 +9,7 @@ from diffusers import StableDiffusionPipeline
 import torch
 from ldm.util import instantiate_from_config
 from main import get_parser
-
+from ldm.modules.diffusionmodules.openaimodel import UNetModel
 if __name__ == "__main__":
     with torch.no_grad():
         yaml_path = "../../train_colossalai.yaml"
@@ -17,7 +17,7 @@ if __name__ == "__main__":
             config = f.read()
         base_config = yaml.load(config, Loader=yaml.FullLoader)
         unet_config = base_config['model']['params']['unet_config']
-        diffusion_model = instantiate_from_config(unet_config).to("cuda:0")
+        diffusion_model = UNetModel(**unet_config.get("params", dict())).to("cuda:0")
 
         pipe = StableDiffusionPipeline.from_pretrained(
             "/data/scratch/diffuser/stable-diffusion-v1-4"

examples/images/diffusion/scripts/txt2img.py

@@ -16,9 +16,9 @@ from torch import autocast
 from contextlib import nullcontext
 from imwatermark import WatermarkEncoder
 
-from ldm.util import instantiate_from_config
 from ldm.models.diffusion.ddim import DDIMSampler
 from ldm.models.diffusion.plms import PLMSSampler
+from ldm.models.diffusion.ddpm import LatentDiffusion
 from ldm.models.diffusion.dpm_solver import DPMSolverSampler
 from utils import replace_module, getModelSize
 
@@ -35,7 +35,7 @@ def load_model_from_config(config, ckpt, verbose=False):
     if "global_step" in pl_sd:
         print(f"Global Step: {pl_sd['global_step']}")
     sd = pl_sd["state_dict"]
-    model = instantiate_from_config(config.model)
+    model = LatentDiffusion(**config.model.get("params", dict()))
     m, u = model.load_state_dict(sd, strict=False)
     if len(m) > 0 and verbose:
         print("missing keys:")