Update to use default diffusers training scripts

args.json

@@ -1,60 +0,0 @@
-{
-  "pretrained_model_name_or_path": "runwayml/stable-diffusion-v1-5",
-  "pretrained_vae_name_or_path": "stabilityai/sd-vae-ft-mse",
-  "revision": "fp16",
-  "tokenizer_name": null,
-  "instance_data_dir": null,
-  "class_data_dir": null,
-  "instance_prompt": null,
-  "class_prompt": null,
-  "save_sample_prompt": "photo of a rhteddy dog",
-  "save_sample_negative_prompt": null,
-  "n_save_sample": 4,
-  "save_guidance_scale": 7.5,
-  "save_infer_steps": 20,
-  "pad_tokens": false,
-  "with_prior_preservation": true,
-  "prior_loss_weight": 1.0,
-  "num_class_images": 200,
-  "output_dir": "/opt/app-root/src/text-to-image-demo/custom/weights/redhat-dog",
-  "seed": 1337,
-  "resolution": 512,
-  "center_crop": false,
-  "train_text_encoder": true,
-  "train_batch_size": 1,
-  "sample_batch_size": 4,
-  "num_train_epochs": 4,
-  "max_train_steps": 800,
-  "gradient_accumulation_steps": 1,
-  "gradient_checkpointing": false,
-  "learning_rate": 1e-06,
-  "scale_lr": false,
-  "lr_scheduler": "constant",
-  "lr_warmup_steps": 0,
-  "use_8bit_adam": true,
-  "adam_beta1": 0.9,
-  "adam_beta2": 0.999,
-  "adam_weight_decay": 0.01,
-  "adam_epsilon": 1e-08,
-  "max_grad_norm": 1.0,
-  "push_to_hub": false,
-  "hub_token": null,
-  "hub_model_id": null,
-  "logging_dir": "logs",
-  "log_interval": 10,
-  "save_interval": 10000,
-  "save_min_steps": 0,
-  "mixed_precision": "fp16",
-  "not_cache_latents": false,
-  "hflip": false,
-  "local_rank": -1,
-  "concepts_list": [
-    {
-      "instance_prompt": "photo of a rhteddy dog",
-      "class_prompt": "a photo of dog",
-      "instance_data_dir": "/opt/app-root/src/text-to-image-demo/custom/data/instance_dir",
-      "class_data_dir": "/opt/app-root/src/text-to-image-demo/custom/data/class_dir"
-    }
-  ],
-  "read_prompts_from_txts": false
-}

unet/diffusion_pytorch_model.bin → checkpoint-500/optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:770b4ef4059a52dd42a7f46f4dd62f46bbc2521a53cb6e95a49b8d9b230aafda
-size 3438375973
+oid sha256:f088d1eff6f69b6b321dea781a1d8279a1fecc1a202bf10ee9e25c7818ce8b54
+size 1725109957

text_encoder/pytorch_model.bin → checkpoint-500/random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2305b3ed9a0a21082bf0ae326d2e0e65c52ef28acb6370fc935bbb9911d3bf9
-size 492308829
+oid sha256:0e73845fc88bfe687b6a9570caeaba8559d5362f771514e8f1986ac94f92ca79
+size 14663

vae/diffusion_pytorch_model.bin → checkpoint-500/scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36bb8e1b54aba3a0914eb35fba13dcb107e9f18d379d1df2158732cd4bf56a94
-size 334711857
+oid sha256:6be622d51c3bcf8a1991c02b9778f31d7e3a79a8b22e03e81a36e25205ef4c5b
+size 563

checkpoint-500/unet/config.json

@@ -0,0 +1,66 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.21.0.dev0",
+  "_name_or_path": "runwayml/stable-diffusion-v1-5",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": 8,
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 768,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 4,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "sample_size": 64,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "transformer_layers_per_block": 1,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": false
+}

checkpoint-500/unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0f5861887c8c2df8f20e2bc61e4c82c06836e01465c948a24f8f9c27baf1fe0
+size 3438167536

feature_extractor/preprocessor_config.json

@@ -14,7 +14,7 @@
     0.4578275,
     0.40821073
   ],
-  "image_processor_type": "CLIPFeatureExtractor",
+  "image_processor_type": "CLIPImageProcessor",
   "image_std": [
     0.26862954,
     0.26130258,

logs/dreambooth/1693358976.7018929/events.out.tfevents.1693358976.text-to-image-0.4436.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:560a0cdf21039623ed3cd0738493453a526242e4405acb3ba5e0f00215f42562
+size 3007

logs/dreambooth/1693358976.70344/hparams.yml

@@ -0,0 +1,58 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+center_crop: false
+checkpointing_steps: 500
+checkpoints_total_limit: null
+class_data_dir: /opt/app-root/src/text-to-image-demo/notebook-output/data/class_dir
+class_labels_conditioning: null
+class_prompt: a photo of dog
+dataloader_num_workers: 0
+enable_xformers_memory_efficient_attention: true
+gradient_accumulation_steps: 1
+gradient_checkpointing: false
+hub_model_id: null
+hub_token: null
+instance_data_dir: /opt/app-root/src/text-to-image-demo/notebook-output/data/instance_dir
+instance_prompt: photo of a rhteddy dog
+learning_rate: 5.0e-06
+local_rank: -1
+logging_dir: logs
+lr_num_cycles: 1
+lr_power: 1.0
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_steps: 800
+mixed_precision: null
+num_class_images: 200
+num_train_epochs: 4
+num_validation_images: 4
+offset_noise: false
+output_dir: /opt/app-root/src/text-to-image-demo/notebook-output/stable_diffusion_weights/redhat-dog
+pre_compute_text_embeddings: false
+pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
+prior_generation_precision: null
+prior_loss_weight: 1.0
+push_to_hub: false
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+sample_batch_size: 4
+scale_lr: false
+seed: null
+set_grads_to_none: false
+skip_save_text_encoder: false
+text_encoder_use_attention_mask: false
+tokenizer_max_length: null
+tokenizer_name: null
+train_batch_size: 1
+train_text_encoder: false
+use_8bit_adam: false
+validation_prompt: null
+validation_scheduler: DPMSolverMultistepScheduler
+validation_steps: 100
+with_prior_preservation: true

logs/dreambooth/1693366191.0888145/events.out.tfevents.1693366191.text-to-image-0.5967.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e52753eb744a0c0bc6dc223673b367087abe2d3216feb29b436390b8c04d3670
+size 3007

logs/dreambooth/1693366191.0903463/hparams.yml

@@ -0,0 +1,58 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+center_crop: false
+checkpointing_steps: 500
+checkpoints_total_limit: null
+class_data_dir: /opt/app-root/src/text-to-image-demo/notebook-output/data/class_dir
+class_labels_conditioning: null
+class_prompt: a photo of dog
+dataloader_num_workers: 0
+enable_xformers_memory_efficient_attention: true
+gradient_accumulation_steps: 2
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+instance_data_dir: /opt/app-root/src/text-to-image-demo/notebook-output/data/instance_dir
+instance_prompt: photo of a rhteddy dog
+learning_rate: 5.0e-06
+local_rank: -1
+logging_dir: logs
+lr_num_cycles: 1
+lr_power: 1.0
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_steps: 800
+mixed_precision: null
+num_class_images: 200
+num_train_epochs: 8
+num_validation_images: 4
+offset_noise: false
+output_dir: /opt/app-root/src/text-to-image-demo/notebook-output/stable_diffusion_weights/redhat-dog
+pre_compute_text_embeddings: false
+pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
+prior_generation_precision: null
+prior_loss_weight: 1.0
+push_to_hub: false
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+sample_batch_size: 4
+scale_lr: false
+seed: null
+set_grads_to_none: false
+skip_save_text_encoder: false
+text_encoder_use_attention_mask: false
+tokenizer_max_length: null
+tokenizer_name: null
+train_batch_size: 1
+train_text_encoder: false
+use_8bit_adam: true
+validation_prompt: null
+validation_scheduler: DPMSolverMultistepScheduler
+validation_steps: 100
+with_prior_preservation: true

logs/dreambooth/1693368952.1649532/events.out.tfevents.1693368952.text-to-image-0.6993.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c8858414d41d75e1ac823f3703064604896f8a21316cb5fa7e5e2d847373d04
+size 3007

logs/dreambooth/1693368952.1666262/hparams.yml

@@ -0,0 +1,58 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+center_crop: false
+checkpointing_steps: 500
+checkpoints_total_limit: null
+class_data_dir: /opt/app-root/src/text-to-image-demo/notebook-output/data/class_dir
+class_labels_conditioning: null
+class_prompt: a photo of dog
+dataloader_num_workers: 0
+enable_xformers_memory_efficient_attention: true
+gradient_accumulation_steps: 2
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+instance_data_dir: /opt/app-root/src/text-to-image-demo/notebook-output/data/instance_dir
+instance_prompt: photo of a rhteddy dog
+learning_rate: 5.0e-06
+local_rank: -1
+logging_dir: logs
+lr_num_cycles: 1
+lr_power: 1.0
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_steps: 800
+mixed_precision: null
+num_class_images: 200
+num_train_epochs: 8
+num_validation_images: 4
+offset_noise: false
+output_dir: /opt/app-root/src/text-to-image-demo/notebook-output/stable_diffusion_weights/redhat-dog
+pre_compute_text_embeddings: false
+pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
+prior_generation_precision: null
+prior_loss_weight: 1.0
+push_to_hub: false
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+sample_batch_size: 4
+scale_lr: false
+seed: null
+set_grads_to_none: false
+skip_save_text_encoder: false
+text_encoder_use_attention_mask: false
+tokenizer_max_length: null
+tokenizer_name: null
+train_batch_size: 1
+train_text_encoder: false
+use_8bit_adam: true
+validation_prompt: null
+validation_scheduler: DPMSolverMultistepScheduler
+validation_steps: 100
+with_prior_preservation: true

logs/dreambooth/1693369738.2229948/events.out.tfevents.1693369738.text-to-image-0.7423.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c7f32b60524f38f3881891fc3238ecfdf4f8994ece65aa640eeb24e95198658
+size 3007

logs/dreambooth/1693369738.2245512/hparams.yml

@@ -0,0 +1,58 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+center_crop: false
+checkpointing_steps: 500
+checkpoints_total_limit: null
+class_data_dir: /opt/app-root/src/text-to-image-demo/notebook-output/data/class_dir
+class_labels_conditioning: null
+class_prompt: a photo of dog
+dataloader_num_workers: 0
+enable_xformers_memory_efficient_attention: true
+gradient_accumulation_steps: 2
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+instance_data_dir: /opt/app-root/src/text-to-image-demo/notebook-output/data/instance_dir
+instance_prompt: photo of a rhteddy dog
+learning_rate: 5.0e-06
+local_rank: -1
+logging_dir: logs
+lr_num_cycles: 1
+lr_power: 1.0
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_steps: 800
+mixed_precision: null
+num_class_images: 200
+num_train_epochs: 8
+num_validation_images: 4
+offset_noise: false
+output_dir: /opt/app-root/src/text-to-image-demo/notebook-output/stable_diffusion_weights/redhat-dog
+pre_compute_text_embeddings: false
+pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
+prior_generation_precision: null
+prior_loss_weight: 1.0
+push_to_hub: false
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+sample_batch_size: 4
+scale_lr: false
+seed: null
+set_grads_to_none: false
+skip_save_text_encoder: false
+text_encoder_use_attention_mask: false
+tokenizer_max_length: null
+tokenizer_name: null
+train_batch_size: 1
+train_text_encoder: false
+use_8bit_adam: true
+validation_prompt: null
+validation_scheduler: DPMSolverMultistepScheduler
+validation_steps: 100
+with_prior_preservation: true

logs/dreambooth/1693369858.7861362/events.out.tfevents.1693369858.text-to-image-0.7601.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b077a286ba05bfd2c12c82ee7d7cf4e1c110d75d08934fb77c72c2786f7818d
+size 3007

logs/dreambooth/1693369858.787858/hparams.yml

@@ -0,0 +1,58 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+center_crop: false
+checkpointing_steps: 500
+checkpoints_total_limit: null
+class_data_dir: /opt/app-root/src/text-to-image-demo/notebook-output/data/class_dir
+class_labels_conditioning: null
+class_prompt: a photo of dog
+dataloader_num_workers: 0
+enable_xformers_memory_efficient_attention: true
+gradient_accumulation_steps: 2
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+instance_data_dir: /opt/app-root/src/text-to-image-demo/notebook-output/data/instance_dir
+instance_prompt: photo of a rhteddy dog
+learning_rate: 5.0e-06
+local_rank: -1
+logging_dir: logs
+lr_num_cycles: 1
+lr_power: 1.0
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_steps: 800
+mixed_precision: null
+num_class_images: 200
+num_train_epochs: 8
+num_validation_images: 4
+offset_noise: false
+output_dir: /opt/app-root/src/text-to-image-demo/notebook-output/stable_diffusion_weights/redhat-dog
+pre_compute_text_embeddings: false
+pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
+prior_generation_precision: null
+prior_loss_weight: 1.0
+push_to_hub: false
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+sample_batch_size: 4
+scale_lr: false
+seed: null
+set_grads_to_none: false
+skip_save_text_encoder: false
+text_encoder_use_attention_mask: false
+tokenizer_max_length: null
+tokenizer_name: null
+train_batch_size: 1
+train_text_encoder: false
+use_8bit_adam: true
+validation_prompt: null
+validation_scheduler: DPMSolverMultistepScheduler
+validation_steps: 100
+with_prior_preservation: true

logs/dreambooth/events.out.tfevents.1693358976.text-to-image-0.4436.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11627ca05f2831fbb4cc906fbc98538bd8375b17a302362203385607ed68df79
+size 66986

logs/dreambooth/events.out.tfevents.1693366191.text-to-image-0.5967.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cce4a92c7044e6b95678faf6d1e42915fff7795e4ac9a7ebeae009c4f3fddfa
+size 133926

logs/dreambooth/events.out.tfevents.1693368952.text-to-image-0.6993.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebc0ae002693c88fff7ce665688e55f809b138323e5997042992f68c0e7277f1
+size 29850

logs/dreambooth/events.out.tfevents.1693369738.text-to-image-0.7423.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92f450e0333ab41c6f808820b9d2996c658785ad4cc3e64ae13212688cd34b02
+size 2906

logs/dreambooth/events.out.tfevents.1693369858.text-to-image-0.7601.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5820131ad19ee973f5856a233d7e8ad264586d5c6b40fcac91feb072d755c1a
+size 133926

model_index.json

@@ -1,14 +1,15 @@
 {
   "_class_name": "StableDiffusionPipeline",
-  "_diffusers_version": "0.15.0.dev0",
+  "_diffusers_version": "0.21.0.dev0",
+  "_name_or_path": "runwayml/stable-diffusion-v1-5",
   "feature_extractor": [
     "transformers",
-    "CLIPFeatureExtractor"
+    "CLIPImageProcessor"
   ],
   "requires_safety_checker": true,
   "safety_checker": [
-    null,
-    null
+    "stable_diffusion",
+    "StableDiffusionSafetyChecker"
   ],
   "scheduler": [
     "diffusers",

safety_checker/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/opt/app-root/src/.cache/huggingface/hub/models--runwayml--stable-diffusion-v1-5/snapshots/1d0c4ebf6ff58a5caecab40fa1406526bca4b5b9/safety_checker",
+  "architectures": [
+    "StableDiffusionSafetyChecker"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
+  "projection_dim": 768,
+  "text_config": {
+    "dropout": 0.0,
+    "hidden_size": 768,
+    "intermediate_size": 3072,
+    "model_type": "clip_text_model",
+    "num_attention_heads": 12
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.32.1",
+  "vision_config": {
+    "dropout": 0.0,
+    "hidden_size": 1024,
+    "intermediate_size": 4096,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14
+  }
+}

safety_checker/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb351a5ded815c3ff744968ad9c6b218d071b9d313d04f35e813b84b4c0ffde8
+size 1215979664

scheduler/scheduler_config.json

@@ -1,18 +1,15 @@
 {
-  "_class_name": "DDIMScheduler",
-  "_diffusers_version": "0.15.0.dev0",
+  "_class_name": "PNDMScheduler",
+  "_diffusers_version": "0.21.0.dev0",
   "beta_end": 0.012,
   "beta_schedule": "scaled_linear",
   "beta_start": 0.00085,
   "clip_sample": false,
-  "clip_sample_range": 1.0,
-  "dynamic_thresholding_ratio": 0.995,
   "num_train_timesteps": 1000,
   "prediction_type": "epsilon",
-  "sample_max_value": 1.0,
   "set_alpha_to_one": false,
   "skip_prk_steps": true,
   "steps_offset": 1,
-  "thresholding": false,
+  "timestep_spacing": "leading",
   "trained_betas": null
 }

text_encoder/config.json

@@ -20,6 +20,6 @@
   "pad_token_id": 1,
   "projection_dim": 768,
   "torch_dtype": "float32",
-  "transformers_version": "4.31.0",
+  "transformers_version": "4.32.1",
   "vocab_size": 49408
 }

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:778d02eb9e707c3fbaae0b67b79ea0d1399b52e624fb634f2f19375ae7c047c3
+size 492265168

unet/config.json

@@ -1,9 +1,13 @@
 {
   "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.15.0.dev0",
+  "_diffusers_version": "0.21.0.dev0",
   "_name_or_path": "runwayml/stable-diffusion-v1-5",
   "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
   "attention_head_dim": 8,
+  "attention_type": "default",
   "block_out_channels": [
     320,
     640,
@@ -16,6 +20,7 @@
   "conv_in_kernel": 3,
   "conv_out_kernel": 3,
   "cross_attention_dim": 768,
+  "cross_attention_norm": null,
   "down_block_types": [
     "CrossAttnDownBlock2D",
     "CrossAttnDownBlock2D",
@@ -24,23 +29,32 @@
   ],
   "downsample_padding": 1,
   "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
   "flip_sin_to_cos": true,
   "freq_shift": 0,
   "in_channels": 4,
   "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
   "mid_block_scale_factor": 1,
   "mid_block_type": "UNetMidBlock2DCrossAttn",
   "norm_eps": 1e-05,
   "norm_num_groups": 32,
+  "num_attention_heads": null,
   "num_class_embeds": null,
   "only_cross_attention": false,
   "out_channels": 4,
   "projection_class_embeddings_input_dim": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
   "resnet_time_scale_shift": "default",
   "sample_size": 64,
   "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
   "time_embedding_type": "positional",
   "timestep_post_act": null,
+  "transformer_layers_per_block": 1,
   "up_block_types": [
     "UpBlock2D",
     "CrossAttnUpBlock2D",

unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12e61c28a03105f2730232cc88b784e7451ba9c0510b88a31a6255460307be22
+size 3438167536

vae/config.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.15.0.dev0",
-  "_name_or_path": "stabilityai/sd-vae-ft-mse",
+  "_diffusers_version": "0.21.0.dev0",
+  "_name_or_path": "/opt/app-root/src/.cache/huggingface/hub/models--runwayml--stable-diffusion-v1-5/snapshots/1d0c4ebf6ff58a5caecab40fa1406526bca4b5b9/vae",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -15,12 +15,13 @@
     "DownEncoderBlock2D",
     "DownEncoderBlock2D"
   ],
+  "force_upcast": true,
   "in_channels": 3,
   "latent_channels": 4,
   "layers_per_block": 2,
   "norm_num_groups": 32,
   "out_channels": 3,
-  "sample_size": 256,
+  "sample_size": 512,
   "scaling_factor": 0.18215,
   "up_block_types": [
     "UpDecoderBlock2D",

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4d2b5932bb4151e54e694fd31ccf51fca908223c9485bd56cd0e1d83ad94c49
+size 334643268