Upload folder using huggingface_hub

checkpoint-300000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dea3dfef93a3d79b99a94113c00e309d5b389b997a4f9b7622766d6c86033d34
+size 6876841875

checkpoint-300000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38634cfb84d7b7fae2cf0a0bc74da16920ac62feeabffdf530412d95af027691
+size 14599

checkpoint-300000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad22c3c5ec18fbcefcdeaed8966966b55e7bbbb3f35933d442f9fa0eb43958b4
+size 557

checkpoint-300000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52884016fcba3f7c2b382b23b287311c9ff6eac8f40c3d403a4e9b5610add0ad
+size 563

checkpoint-300000/unet/config.json

@@ -0,0 +1,62 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.17.0.dev0",
+  "_name_or_path": "/data/pix2pix-riff-ckpt/checkpoint-180000",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "attention_head_dim": 8,
+  "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": 8,
+  "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_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": 32,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": false
+}

checkpoint-300000/unet/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dd649c4136eec574184838a8a8d3a24d9c2243ed5e8b181aa1856840acdcdf2
+size 3438422053

config.json

@@ -0,0 +1,62 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.17.0.dev0",
+  "_name_or_path": "riffusion/riffusion-model-v1",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "attention_head_dim": 8,
+  "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": 8,
+  "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_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": 32,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": false
+}

feature_extractor/preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

logs/instruct-pix2pix/1686024460.013109/events.out.tfevents.1686024460.ip-172-31-28-175.ec2.internal.5327.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70e92e71f365ffe4f9f5b9805891bb5a3f26e8133f28c095459b182b1fb8a9c7
+size 2517

logs/instruct-pix2pix/1686024460.0144317/hparams.yml

@@ -0,0 +1,50 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+cache_dir: null
+center_crop: false
+checkpointing_steps: 5000
+checkpoints_total_limit: 3
+conditioning_dropout_prob: 0.05
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: zachary-shah/musdb18-spec-pix2pix
+edit_prompt_column: edit_prompt
+edited_image_column: edited_image
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+hub_model_id: zachary-shah/riff-pix2pix-v1
+hub_token: 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
+learning_rate: 0.0001
+local_rank: -1
+logging_dir: logs
+lr_scheduler: constant
+lr_warmup_steps: 500
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 3155600
+mixed_precision: null
+non_ema_revision: null
+num_train_epochs: 100
+num_validation_images: 4
+original_image_column: original_image
+output_dir: /data/pix2pix-riff-model
+pretrained_model_name_or_path: riffusion/riffusion-model-v1
+push_to_hub: true
+random_flip: false
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: 0
+train_batch_size: 1
+train_data_dir: null
+use_8bit_adam: false
+use_ema: false
+val_image_url: null
+validation_epochs: 1
+validation_prompt: null

logs/instruct-pix2pix/1686024636.282702/events.out.tfevents.1686024636.ip-172-31-28-175.ec2.internal.6891.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:094cb4a49399d47a411c7939816a49908f0fe276d67f425c369674d3ca11a6cb
+size 2572

logs/instruct-pix2pix/1686024636.2839978/hparams.yml

@@ -0,0 +1,50 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+cache_dir: null
+center_crop: false
+checkpointing_steps: 5000
+checkpoints_total_limit: 3
+conditioning_dropout_prob: 0.05
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: zachary-shah/musdb18-spec-pix2pix
+edit_prompt_column: edit_prompt
+edited_image_column: edited_image
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+hub_model_id: zachary-shah/riff-pix2pix-v1
+hub_token: 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
+learning_rate: 0.0001
+local_rank: -1
+logging_dir: logs
+lr_scheduler: constant
+lr_warmup_steps: 500
+max_grad_norm: 1.0
+max_train_samples: 10000
+max_train_steps: 500000
+mixed_precision: null
+non_ema_revision: null
+num_train_epochs: 100
+num_validation_images: 4
+original_image_column: original_image
+output_dir: /data/pix2pix-riff-model
+pretrained_model_name_or_path: riffusion/riffusion-model-v1
+push_to_hub: true
+random_flip: false
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: 0
+train_batch_size: 2
+train_data_dir: null
+use_8bit_adam: false
+use_ema: false
+val_image_url: null
+validation_epochs: 1
+validation_prompt: null

logs/instruct-pix2pix/1686024669.0956256/events.out.tfevents.1686024669.ip-172-31-28-175.ec2.internal.7120.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb32fc8d68d140bffed2b80231a3fada25d3c6f11305d1799da8b02351c33601
+size 2572

logs/instruct-pix2pix/1686024669.0970294/hparams.yml

@@ -0,0 +1,50 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+cache_dir: null
+center_crop: false
+checkpointing_steps: 5000
+checkpoints_total_limit: 3
+conditioning_dropout_prob: 0.05
+dataloader_num_workers: 16
+dataset_config_name: null
+dataset_name: zachary-shah/musdb18-spec-pix2pix
+edit_prompt_column: edit_prompt
+edited_image_column: edited_image
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+hub_model_id: zachary-shah/riff-pix2pix-v1
+hub_token: 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
+learning_rate: 0.0001
+local_rank: -1
+logging_dir: logs
+lr_scheduler: constant
+lr_warmup_steps: 500
+max_grad_norm: 1.0
+max_train_samples: 10000
+max_train_steps: 500000
+mixed_precision: null
+non_ema_revision: null
+num_train_epochs: 100
+num_validation_images: 4
+original_image_column: original_image
+output_dir: /data/pix2pix-riff-model
+pretrained_model_name_or_path: riffusion/riffusion-model-v1
+push_to_hub: true
+random_flip: false
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: 0
+train_batch_size: 2
+train_data_dir: null
+use_8bit_adam: false
+use_ema: false
+val_image_url: null
+validation_epochs: 1
+validation_prompt: null

logs/instruct-pix2pix/1686024697.2151372/events.out.tfevents.1686024697.ip-172-31-28-175.ec2.internal.7629.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eeec7568326ac022e03c6034b9d07382fb876994675baa9ffbc5f2bba04049e3
+size 2572

logs/instruct-pix2pix/1686024697.2164345/hparams.yml

@@ -0,0 +1,50 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+cache_dir: null
+center_crop: false
+checkpointing_steps: 5000
+checkpoints_total_limit: 3
+conditioning_dropout_prob: 0.05
+dataloader_num_workers: 16
+dataset_config_name: null
+dataset_name: zachary-shah/musdb18-spec-pix2pix
+edit_prompt_column: edit_prompt
+edited_image_column: edited_image
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+gradient_checkpointing: false
+hub_model_id: zachary-shah/riff-pix2pix-v1
+hub_token: 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
+learning_rate: 0.0001
+local_rank: -1
+logging_dir: logs
+lr_scheduler: constant
+lr_warmup_steps: 500
+max_grad_norm: 1.0
+max_train_samples: 10000
+max_train_steps: 500000
+mixed_precision: null
+non_ema_revision: null
+num_train_epochs: 100
+num_validation_images: 4
+original_image_column: original_image
+output_dir: /data/pix2pix-riff-model
+pretrained_model_name_or_path: riffusion/riffusion-model-v1
+push_to_hub: true
+random_flip: false
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: 0
+train_batch_size: 2
+train_data_dir: null
+use_8bit_adam: false
+use_ema: false
+val_image_url: null
+validation_epochs: 1
+validation_prompt: null

logs/instruct-pix2pix/1686024729.483795/events.out.tfevents.1686024729.ip-172-31-28-175.ec2.internal.8161.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06d687072fe6406428b40e46c1d762b6e271ff2db85935522242e6eb58b56f80
+size 2572

logs/instruct-pix2pix/1686024729.4851048/hparams.yml

@@ -0,0 +1,50 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+cache_dir: null
+center_crop: false
+checkpointing_steps: 5000
+checkpoints_total_limit: 3
+conditioning_dropout_prob: 0.05
+dataloader_num_workers: 16
+dataset_config_name: null
+dataset_name: zachary-shah/musdb18-spec-pix2pix
+edit_prompt_column: edit_prompt
+edited_image_column: edited_image
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+gradient_checkpointing: false
+hub_model_id: zachary-shah/riff-pix2pix-v1
+hub_token: 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
+learning_rate: 0.0001
+local_rank: -1
+logging_dir: logs
+lr_scheduler: constant
+lr_warmup_steps: 500
+max_grad_norm: 1.0
+max_train_samples: 10000
+max_train_steps: 250000
+mixed_precision: null
+non_ema_revision: null
+num_train_epochs: 100
+num_validation_images: 4
+original_image_column: original_image
+output_dir: /data/pix2pix-riff-model
+pretrained_model_name_or_path: riffusion/riffusion-model-v1
+push_to_hub: true
+random_flip: false
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: 0
+train_batch_size: 4
+train_data_dir: null
+use_8bit_adam: false
+use_ema: false
+val_image_url: null
+validation_epochs: 1
+validation_prompt: null

logs/instruct-pix2pix/1686251434.2604456/events.out.tfevents.1686251434.ip-172-31-28-175.ec2.internal.7700.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec566f287a78901fc6b296e67adc61a4739e24e9c3dc7c8f0d3bd000845b33fc
+size 2616

logs/instruct-pix2pix/1686251434.2618048/hparams.yml

@@ -0,0 +1,50 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+cache_dir: null
+center_crop: false
+checkpointing_steps: 30000
+checkpoints_total_limit: 3
+conditioning_dropout_prob: 0.05
+dataloader_num_workers: 16
+dataset_config_name: null
+dataset_name: zachary-shah/musdb18-spec-pix2pix
+edit_prompt_column: edit_prompt
+edited_image_column: edited_image
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+gradient_checkpointing: false
+hub_model_id: zachary-shah/riff-pix2pix-v1
+hub_token: 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
+learning_rate: 0.0001
+local_rank: -1
+logging_dir: logs
+lr_scheduler: constant
+lr_warmup_steps: 500
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 90000
+mixed_precision: null
+non_ema_revision: null
+num_train_epochs: 12
+num_validation_images: 4
+original_image_column: original_image
+output_dir: /data/pix2pix-riff-ckpt
+pretrained_model_name_or_path: riffusion/riffusion-model-v1
+push_to_hub: true
+random_flip: false
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: /data/pix2pix-riff-ckpt/checkpoint-180000/
+revision: null
+scale_lr: false
+seed: 0
+train_batch_size: 4
+train_data_dir: null
+use_8bit_adam: false
+use_ema: false
+val_image_url: null
+validation_epochs: 1
+validation_prompt: null

logs/instruct-pix2pix/1686251604.0436833/events.out.tfevents.1686251604.ip-172-31-28-175.ec2.internal.8878.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:959d06c122d8f48e5a0173d3daa861a6ea664809a76a843b33664e5093fb4fd8
+size 2616

logs/instruct-pix2pix/1686251604.045071/hparams.yml

@@ -0,0 +1,50 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+cache_dir: null
+center_crop: false
+checkpointing_steps: 30000
+checkpoints_total_limit: 3
+conditioning_dropout_prob: 0.05
+dataloader_num_workers: 16
+dataset_config_name: null
+dataset_name: zachary-shah/musdb18-spec-pix2pix
+edit_prompt_column: edit_prompt
+edited_image_column: edited_image
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+gradient_checkpointing: false
+hub_model_id: zachary-shah/riff-pix2pix-v1
+hub_token: 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
+learning_rate: 0.0001
+local_rank: -1
+logging_dir: logs
+lr_scheduler: constant
+lr_warmup_steps: 500
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 90000
+mixed_precision: null
+non_ema_revision: null
+num_train_epochs: 12
+num_validation_images: 4
+original_image_column: original_image
+output_dir: /data/pix2pix-riff-ckpt
+pretrained_model_name_or_path: riffusion/riffusion-model-v1
+push_to_hub: true
+random_flip: false
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: /data/pix2pix-riff-ckpt/checkpoint-180000/
+revision: null
+scale_lr: false
+seed: 0
+train_batch_size: 4
+train_data_dir: null
+use_8bit_adam: false
+use_ema: false
+val_image_url: null
+validation_epochs: 1
+validation_prompt: null

logs/instruct-pix2pix/1686251721.46846/events.out.tfevents.1686251721.ip-172-31-28-175.ec2.internal.9638.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eaef5f7ffc6658be93bef1e6a97c2e1ecd156b65634441d56d4da7e750dd940
+size 2616

logs/instruct-pix2pix/1686251721.4697907/hparams.yml

@@ -0,0 +1,50 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+cache_dir: null
+center_crop: false
+checkpointing_steps: 30000
+checkpoints_total_limit: 3
+conditioning_dropout_prob: 0.05
+dataloader_num_workers: 16
+dataset_config_name: null
+dataset_name: zachary-shah/musdb18-spec-pix2pix
+edit_prompt_column: edit_prompt
+edited_image_column: edited_image
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+gradient_checkpointing: false
+hub_model_id: zachary-shah/riff-pix2pix-v1
+hub_token: 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
+learning_rate: 0.0001
+local_rank: -1
+logging_dir: logs
+lr_scheduler: constant
+lr_warmup_steps: 500
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 90000
+mixed_precision: null
+non_ema_revision: null
+num_train_epochs: 12
+num_validation_images: 4
+original_image_column: original_image
+output_dir: /data/pix2pix-riff-ckpt
+pretrained_model_name_or_path: riffusion/riffusion-model-v1
+push_to_hub: true
+random_flip: false
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: /data/pix2pix-riff-ckpt/checkpoint-180000/
+revision: null
+scale_lr: false
+seed: 0
+train_batch_size: 4
+train_data_dir: null
+use_8bit_adam: false
+use_ema: false
+val_image_url: null
+validation_epochs: 1
+validation_prompt: null

logs/instruct-pix2pix/1686251843.1085622/events.out.tfevents.1686251843.ip-172-31-28-175.ec2.internal.10427.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d5c4a7118afbdd52b0714d114e87336d5fceb1c07aebe2ccef38f5b9f93edf4
+size 2616

logs/instruct-pix2pix/1686251843.1098614/hparams.yml

@@ -0,0 +1,50 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+cache_dir: null
+center_crop: false
+checkpointing_steps: 30000
+checkpoints_total_limit: 3
+conditioning_dropout_prob: 0.05
+dataloader_num_workers: 16
+dataset_config_name: null
+dataset_name: zachary-shah/musdb18-spec-pix2pix
+edit_prompt_column: edit_prompt
+edited_image_column: edited_image
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+gradient_checkpointing: false
+hub_model_id: zachary-shah/riff-pix2pix-v1
+hub_token: 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
+learning_rate: 0.0001
+local_rank: -1
+logging_dir: logs
+lr_scheduler: constant
+lr_warmup_steps: 500
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 90000
+mixed_precision: null
+non_ema_revision: null
+num_train_epochs: 12
+num_validation_images: 4
+original_image_column: original_image
+output_dir: /data/pix2pix-riff-ckpt
+pretrained_model_name_or_path: riffusion/riffusion-model-v1
+push_to_hub: true
+random_flip: false
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: /data/pix2pix-riff-ckpt/checkpoint-180000/
+revision: null
+scale_lr: false
+seed: 0
+train_batch_size: 4
+train_data_dir: null
+use_8bit_adam: false
+use_ema: false
+val_image_url: null
+validation_epochs: 1
+validation_prompt: null

logs/instruct-pix2pix/1686252476.5714889/events.out.tfevents.1686252476.ip-172-31-28-175.ec2.internal.14778.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e714f4134332fdb3873a3cc9cb6fa814eb068953d2125a9a3419d7c48abbe7e3
+size 2580

logs/instruct-pix2pix/1686252476.5728323/hparams.yml

@@ -0,0 +1,50 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+cache_dir: null
+center_crop: false
+checkpointing_steps: 30000
+checkpoints_total_limit: 3
+conditioning_dropout_prob: 0.05
+dataloader_num_workers: 16
+dataset_config_name: null
+dataset_name: zachary-shah/musdb18-spec-pix2pix
+edit_prompt_column: edit_prompt
+edited_image_column: edited_image
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+gradient_checkpointing: false
+hub_model_id: zachary-shah/riff-pix2pix-v1
+hub_token: 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
+learning_rate: 0.0001
+local_rank: -1
+logging_dir: logs
+lr_scheduler: constant
+lr_warmup_steps: 500
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 90000
+mixed_precision: null
+non_ema_revision: null
+num_train_epochs: 12
+num_validation_images: 4
+original_image_column: original_image
+output_dir: /data/pix2pix-riff-ckpt
+pretrained_model_name_or_path: riffusion/riffusion-model-v1
+push_to_hub: true
+random_flip: false
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: latest
+revision: null
+scale_lr: false
+seed: 0
+train_batch_size: 4
+train_data_dir: null
+use_8bit_adam: false
+use_ema: false
+val_image_url: null
+validation_epochs: 1
+validation_prompt: null

logs/instruct-pix2pix/1686252763.501972/events.out.tfevents.1686252763.ip-172-31-28-175.ec2.internal.16627.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8673a3c8e68994f0f95e1949a8bb7b34bccb5508bbda13d15400792f043c77e
+size 2445

logs/instruct-pix2pix/1686252763.5033057/hparams.yml

@@ -0,0 +1,50 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+cache_dir: null
+center_crop: false
+checkpointing_steps: 30000
+checkpoints_total_limit: 3
+conditioning_dropout_prob: 0.05
+dataloader_num_workers: 16
+dataset_config_name: null
+dataset_name: zachary-shah/musdb18-spec-pix2pix
+edit_prompt_column: edit_prompt
+edited_image_column: edited_image
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+gradient_checkpointing: false
+hub_model_id: null
+hub_token: null
+learning_rate: 0.0001
+local_rank: -1
+logging_dir: logs
+lr_scheduler: constant
+lr_warmup_steps: 500
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 90000
+mixed_precision: null
+non_ema_revision: null
+num_train_epochs: 12
+num_validation_images: 4
+original_image_column: original_image
+output_dir: /data/pix2pix-riff-ckpt
+pretrained_model_name_or_path: riffusion/riffusion-model-v1
+push_to_hub: false
+random_flip: false
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: latest
+revision: null
+scale_lr: false
+seed: 0
+train_batch_size: 4
+train_data_dir: null
+use_8bit_adam: false
+use_ema: false
+val_image_url: null
+validation_epochs: 1
+validation_prompt: null

logs/instruct-pix2pix/1686253046.6994145/events.out.tfevents.1686253046.ip-172-31-28-175.ec2.internal.18316.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42ae038d19aaaaeb63193e36fbf8877abff72d4b6b1a4e281d91a73fcb0574f1
+size 2445

logs/instruct-pix2pix/1686253046.7006776/hparams.yml

@@ -0,0 +1,50 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+cache_dir: null
+center_crop: false
+checkpointing_steps: 30000
+checkpoints_total_limit: 3
+conditioning_dropout_prob: 0.05
+dataloader_num_workers: 16
+dataset_config_name: null
+dataset_name: zachary-shah/musdb18-spec-pix2pix
+edit_prompt_column: edit_prompt
+edited_image_column: edited_image
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+gradient_checkpointing: false
+hub_model_id: null
+hub_token: null
+learning_rate: 0.0001
+local_rank: -1
+logging_dir: logs
+lr_scheduler: constant
+lr_warmup_steps: 500
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 300000
+mixed_precision: null
+non_ema_revision: null
+num_train_epochs: 39
+num_validation_images: 4
+original_image_column: original_image
+output_dir: /data/pix2pix-riff-ckpt
+pretrained_model_name_or_path: riffusion/riffusion-model-v1
+push_to_hub: false
+random_flip: false
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: latest
+revision: null
+scale_lr: false
+seed: 0
+train_batch_size: 4
+train_data_dir: null
+use_8bit_adam: false
+use_ema: false
+val_image_url: null
+validation_epochs: 1
+validation_prompt: null

logs/instruct-pix2pix/events.out.tfevents.1686024460.ip-172-31-28-175.ec2.internal.5327.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0bc80c7606adc4c35795167230ce29abd5c260f81e5b190fd6e30892c3c4f49
+size 10594

logs/instruct-pix2pix/events.out.tfevents.1686024636.ip-172-31-28-175.ec2.internal.6891.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92ce01e3cc5a9de6da973a097506826d35ff7d86f9372015074e384382eb9690
+size 1048

logs/instruct-pix2pix/events.out.tfevents.1686024669.ip-172-31-28-175.ec2.internal.7120.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee4749ebf1ab093ec0b7e0c39ac0a15194303b638bf43178f2240b114d42a363
+size 760

logs/instruct-pix2pix/events.out.tfevents.1686024697.ip-172-31-28-175.ec2.internal.7629.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fccb7a532594f91451ae0556fc5164771664566a587b6ff818411116c9046bc6
+size 1096

logs/instruct-pix2pix/events.out.tfevents.1686024729.ip-172-31-28-175.ec2.internal.8161.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d01329bca2af463822c468097e6aee83f6f396821a9068e4270ea10cc5761ab1
+size 9233578

logs/instruct-pix2pix/events.out.tfevents.1686251434.ip-172-31-28-175.ec2.internal.7700.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6302e2e10b20728537497f5440de51c95a733b184a23174eb805d46e583408a
+size 88

logs/instruct-pix2pix/events.out.tfevents.1686251604.ip-172-31-28-175.ec2.internal.8878.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b58d92dc8f123b31126b909885c3bfc2377b964f7a0139b56d32b847cad5fd6
+size 88

logs/instruct-pix2pix/events.out.tfevents.1686251721.ip-172-31-28-175.ec2.internal.9638.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f71e6a69e224c8f1ddf62484791c965bfb0f11928358fc86ac6b8b9e6409b2e4
+size 88

logs/instruct-pix2pix/events.out.tfevents.1686251843.ip-172-31-28-175.ec2.internal.10427.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faf3444a25ace3559de379bae211bac1d761309f83a285681655f8109500e7d9
+size 88

logs/instruct-pix2pix/events.out.tfevents.1686252476.ip-172-31-28-175.ec2.internal.14778.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d145d31694b71d66fa868fd5ff08be6369fa310902405247a1eeaf1a0a2c9441
+size 88

logs/instruct-pix2pix/events.out.tfevents.1686252763.ip-172-31-28-175.ec2.internal.16627.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fc48a70440cc2e40e336598cf0212c81e7d363e735f70f16f0937a309cb5965
+size 88

logs/instruct-pix2pix/events.out.tfevents.1686253046.ip-172-31-28-175.ec2.internal.18316.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a871741152bd129716652a92867928d464780d484590fc46e2d333373ce26c99
+size 6000088

model_index.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "StableDiffusionInstructPix2PixPipeline",
+  "_diffusers_version": "0.17.0.dev0",
+  "feature_extractor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "requires_safety_checker": true,
+  "safety_checker": [
+    "stable_diffusion",
+    "StableDiffusionSafetyChecker"
+  ],
+  "scheduler": [
+    "diffusers",
+    "PNDMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

safety_checker/config.json

@@ -0,0 +1,168 @@
+{
+  "_commit_hash": "8f2e752c74e8316c6eb4fdaa6598a46ce1d88af5",
+  "_name_or_path": "/home/ec2-user/.cache/huggingface/hub/models--riffusion--riffusion-model-v1/snapshots/8f2e752c74e8316c6eb4fdaa6598a46ce1d88af5/safety_checker",
+  "architectures": [
+    "StableDiffusionSafetyChecker"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
+  "projection_dim": 768,
+  "text_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 77,
+    "min_length": 0,
+    "model_type": "clip_text_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 512,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.29.2",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vocab_size": 49408
+  },
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "clip_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 14,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 512,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.29.2",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  }
+}

safety_checker/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16d28f2b37109f222cdc33620fdd262102ac32112be0352a7f77e9614b35a394
+size 1216064769

scheduler/scheduler_config.json

@@ -0,0 +1,13 @@
+{
+  "_class_name": "PNDMScheduler",
+  "_diffusers_version": "0.17.0.dev0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "trained_betas": null
+}

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "riffusion/riffusion-model-v1",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "projection_dim": 768,
+  "torch_dtype": "float16",
+  "transformers_version": "4.29.2",
+  "vocab_size": 49408
+}

text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a34f30098988d85dc0fb0fc272a842ebcf552e2ebc6ce4adbcf3695d08e8a90
+size 246188833