End of training

README.md

@@ -0,0 +1,17 @@
+
+---
+license: creativeml-openrail-m
+base_model: stabilityai/stable-diffusion-2-depth
+tags:
+- stable-diffusion
+- stable-diffusion-diffusers
+- text-to-image
+- diffusers
+- textual_inversion
+inference: true
+---
+    
+# Textual inversion text2image fine-tuning - AACEE/textual_inversion_airship
+These are textual inversion adaption weights for stabilityai/stable-diffusion-2-depth. You can find some example images in the following. 
+
+

checkpoint-1000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23843dd109ab96f532f7947ece14d42af61e4121051d27455d9d8525f74ce914
+size 404760109

checkpoint-1000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b2b4839f76036bdd1278c775724adb0ded9b1c71f9c4830baeeadc0ff6f9214
+size 1361701921

checkpoint-1000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e6c23a656e765c3bfff1a0c2364146992585fab8f0ab8f25ce35a003cef2bbe
+size 14727

checkpoint-1000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbb19b948b33a080098712534e53a991114e50367c7efbe3f9b4d0cec03eb540
+size 563

checkpoint-1500/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fc60b8c39a4ae0dc9446827653cca9360bd26d889916caee599c602ed958202
+size 404760109

checkpoint-1500/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:431423c25334ca77ac408fb3556d76e9700fcd3bdca3fceb4d74a08a37bcb13f
+size 1361701921

checkpoint-1500/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a124397d6d5026d0c35940240b002de4912dfefaaaa90d991329e762911b8d5
+size 14727

checkpoint-1500/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7abf0b3af2013b920618166f35e17d899fce776df72f2c2a64c13989f4b8a6a8
+size 563

checkpoint-2000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6148f1d344ee8182734b9e509c914f0ca07a780f9c2c4da0fe6291f0812043c5
+size 404760109

checkpoint-2000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d59ee73289bf80c81e20cb7fe3dedc73e7aa7087a8fba2e49b2643aa7d7a32f
+size 1361701921

checkpoint-2000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6791c242e5e1914ef066ce2018151f2cbaab5ca2129b0b158420e577ae7a58b0
+size 14727

checkpoint-2000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ce55ada40659c32ea01f44d7732f0406a6c9004376f7e5579de396b3481cc2d
+size 563

checkpoint-2500/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c3535e3215895a5d2cd8c0661176493fb07622799edf0f02395561225ee6aa7
+size 404760109

checkpoint-2500/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dcecab69287163c3be01031acd35179252bcf2fdbfe7be35a72542e96d33f05
+size 1361701921

checkpoint-2500/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b59ca7544c967d34ce241ff04c494875b84102d7f7797058b3c8f7e87169fe38
+size 14663

checkpoint-2500/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:496e5a35d8686f4bf9ce59c376f5f501ec4a1034cf3b70deb1f3d2c047fab2d4
+size 563

checkpoint-3000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35fbe6eba4f62a6654e7461bb48779343204c8f5dc0995839b8dfef51c9fe88b
+size 404760109

checkpoint-3000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bc9dd53d6dd935c444e348a30ecfeabd97fbd017aa1ac257fa7237838bfe927
+size 1361701921

checkpoint-3000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e103932012b1e88813ecdc5ce109ffabb75c7802144f400fe93df000df6c5bf0
+size 14663

checkpoint-3000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2056b541ceef5d77999a48951b85854f6503b83d58bc070e970ec3531e56e169
+size 563

checkpoint-500/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b712f29ed6bdde56e458211686be679fb95b947cb7e29f41aad25230770e2cf
+size 404760109

checkpoint-500/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b26d574dfc81b6aa78e452773e4205c1af8b107e3f3ecc1115eecea045805c43
+size 1361701921

checkpoint-500/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6c8bc773b36b50e59341001b629f7d1f1c74e58a31ff33b1cedc36d06521f01
+size 14727

checkpoint-500/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:478ff7b9adcb1fba8f74abd29e0dfb41133888ecf608d07ea8ae2143e019d098
+size 563

feature_extractor/preprocessor_config.json

@@ -0,0 +1,24 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "ensure_multiple_of": 1,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "DPTImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "keep_aspect_ratio": false,
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 384,
+    "width": 384
+  }
+}

learned_embeds-steps-1000.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9e8290d0ab2dddac829dfb72469327d326f57307b72a9c671a9ef045acc5335
+size 5025

learned_embeds-steps-1500.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebd9adc8be43f2b5048e42b5aee238ee30470ebc27d07eb33fe48a5128c9d5b6
+size 5025

learned_embeds-steps-2000.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c336bc05dba700b892c45b4b362bb8046951dee1b3a90e7a7c95352818b2e907
+size 5025

learned_embeds-steps-2500.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e082849a8b2d3dfde8ba1bdd18d1c9e74b0f84382577a1332889dc9796692869
+size 5025

learned_embeds-steps-3000.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b41f23a9759253ece788cfd391baa00f08972184cb55bc2ea15614d25de3f81
+size 5025

learned_embeds-steps-500.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41d7d7f77009fd95ba5ab5a8591a5d92dda258592de44f491e772a772549e8ef
+size 5022

learned_embeds.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44b6a7993abb6c86e65208f4230079ecffe21884f9b74c8202e79d83dfadf1cf
+size 4864

logs/textual_inversion/1688816940.4384546/events.out.tfevents.1688816940.p4de-st-p4de24xlarge-603.1040665.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c76548792109e5be2e98a1b2ebf35dea6cd2253cbd6fa4e18a23ecf361ceabae
+size 2645

logs/textual_inversion/1688816940.4492185/hparams.yml

@@ -0,0 +1,47 @@
+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
+dataloader_num_workers: 0
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+hub_model_id: null
+hub_token: null
+initializer_token: ship
+learnable_property: object
+learning_rate: 0.002
+local_rank: -1
+logging_dir: logs
+lr_num_cycles: 1
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_train_steps: 3000
+mixed_precision: 'no'
+num_train_epochs: 1
+num_validation_images: 8
+num_vectors: 1
+output_dir: textual_inversion_airship
+placeholder_token: <sks airship>
+pretrained_model_name_or_path: stabilityai/stable-diffusion-2-depth
+push_to_hub: true
+repeats: 100
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+save_as_full_pipeline: false
+save_steps: 500
+scale_lr: true
+seed: null
+tokenizer_name: null
+train_batch_size: 1
+train_data_dir: /fsx-home/ancao/source/threestudio/outputs/dreamfusion-depth-refine-textured-mesh/sks_airship@20230702-155105/save/it10000-rgb
+train_depth_dir: /fsx-home/ancao/source/threestudio/outputs/dreamfusion-depth-refine-textured-mesh/sks_airship@20230702-155105/save/it10000-depth
+validation_epochs: null
+validation_prompt: a photo of <sks airship>
+validation_steps: 100

logs/textual_inversion/1688822721.2017686/events.out.tfevents.1688822721.p4de-st-p4de24xlarge-603.1196897.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5418a7fbb49b0f8e9818ab53c0a90cd2026846b35d9bd78789fc507296c6a4bb
+size 2573

logs/textual_inversion/1688822721.216645/hparams.yml

@@ -0,0 +1,47 @@
+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
+dataloader_num_workers: 0
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+hub_model_id: null
+hub_token: null
+initializer_token: ship
+learnable_property: object
+learning_rate: 0.002
+local_rank: -1
+logging_dir: logs
+lr_num_cycles: 1
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_train_steps: 3000
+mixed_precision: 'no'
+num_train_epochs: 1
+num_validation_images: 4
+num_vectors: 1
+output_dir: textual_inversion_airship
+placeholder_token: <sks airship>
+pretrained_model_name_or_path: stabilityai/stable-diffusion-2-depth
+push_to_hub: true
+repeats: 100
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+save_as_full_pipeline: false
+save_steps: 500
+scale_lr: true
+seed: null
+tokenizer_name: null
+train_batch_size: 1
+train_data_dir: /fsx-home/ancao/source/threestudio/outputs/dreamfusion-depth-refine-textured-mesh/sks_airship@20230702-155105/save/it10000-rgb
+train_depth_dir: /fsx-home/ancao/source/threestudio/outputs/dreamfusion-depth-refine-textured-mesh/sks_airship@20230702-155105/save/it10000-depth
+validation_epochs: null
+validation_prompt: null
+validation_steps: 100

logs/textual_inversion/events.out.tfevents.1688816940.p4de-st-p4de24xlarge-603.1040665.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13e4ea06dc05f806e8b6a4a64a6595b48f73980f521e1be3c684721c4c113ac4
+size 32794

logs/textual_inversion/events.out.tfevents.1688822721.p4de-st-p4de24xlarge-603.1196897.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1824f9c15a172c136c2804a25fed4085fb36d227897bcb1c985d2bc63f0cdd03
+size 1007054

model_index.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.18.1",
+  "feature_extractor": [
+    "transformers",
+    "DPTImageProcessor"
+  ],
+  "requires_safety_checker": true,
+  "safety_checker": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "PNDMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,15 @@
+{
+  "_class_name": "PNDMScheduler",
+  "_diffusers_version": "0.18.1",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "timestep_spacing": "leading",
+  "trained_betas": null
+}

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "stabilityai/stable-diffusion-2-depth",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_size": 1024,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 23,
+  "pad_token_id": 1,
+  "projection_dim": 512,
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.2",
+  "vocab_size": 49409
+}

text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daba24ccdbb33dc6d8d59463c4ae1ea5e0b52e56c85471166fe939ad9b262424
+size 1361684001

tokenizer/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<sks airship>": 49408
+}

tokenizer/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "!",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

unet/config.json

@@ -0,0 +1,70 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.18.1",
+  "_name_or_path": "stabilityai/stable-diffusion-2-depth",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": [
+    5,
+    10,
+    20,
+    20
+  ],
+  "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": 1024,
+  "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": 5,
+  "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": 32,
+  "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": true
+}

unet/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87e1d440b0aca6f6e4590d30495a59c920fdb40419f5c9bf82dcd47b5bf21016
+size 3463946213