End of training

README.md

@@ -1,17 +1,22 @@
 
 ---
 license: creativeml-openrail-m
-base_model: stabilityai/stable-diffusion-2-1
+base_model: runwayml/stable-diffusion-v1-5
+instance_prompt: a centered satellite photo of <annual-crop> annual crop land.
 tags:
 - stable-diffusion
 - stable-diffusion-diffusers
 - text-to-image
 - diffusers
-- textual_inversion
+- dreambooth
 inference: true
 ---
     
-# Textual inversion text2image fine-tuning - ashnrk/textual_inversion_annual_crop
-These are textual inversion adaption weights for stabilityai/stable-diffusion-2-1. You can find some example images in the following. 
+# DreamBooth - ashnrk/textual_inversion_annual_crop
 
+This is a dreambooth model derived from runwayml/stable-diffusion-v1-5. The weights were trained on a centered satellite photo of <annual-crop> annual crop land. using [DreamBooth](https://dreambooth.github.io/).
+You can find some example images in the following. 
 
+
+
+DreamBooth for the text encoder was enabled: False.

logs/dreambooth/1689372202.428514/events.out.tfevents.1689372202.ip-172-31-25-234.2454530.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d5fc5e3bf670c96693c3c2d479881ddcdcca5e2a481e9a29ba0945aaa9f5564
+size 2775

logs/dreambooth/1689372202.4301002/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: null
+class_labels_conditioning: null
+class_prompt: null
+dataloader_num_workers: 0
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+gradient_checkpointing: false
+hub_model_id: null
+hub_token: null
+instance_data_dir: /home/ubuntu/datasets/Eurosat_few_shot_10/AnnualCrop
+instance_prompt: a centered satellite photo of <annual-crop> annual crop land.
+learning_rate: 5.0e-06
+local_rank: 0
+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: 200
+mixed_precision: null
+num_class_images: 100
+num_train_epochs: 100
+num_validation_images: 4
+offset_noise: false
+output_dir: textual_inversion_annual_crop
+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: true
+report_to: tensorboard
+resolution: 64
+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_images: null
+validation_prompt: null
+validation_steps: 100
+with_prior_preservation: false

logs/dreambooth/events.out.tfevents.1689372202.ip-172-31-25-234.2454530.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:900c8c74207bee319075ba5ade3e3ebe1dcf003c8d17644a2ff327cd276e85f2
+size 16634

model_index.json

@@ -5,14 +5,14 @@
     "transformers",
     "CLIPImageProcessor"
   ],
-  "requires_safety_checker": false,
+  "requires_safety_checker": true,
   "safety_checker": [
-    null,
-    null
+    "stable_diffusion",
+    "StableDiffusionSafetyChecker"
   ],
   "scheduler": [
     "diffusers",
-    "DDIMScheduler"
+    "PNDMScheduler"
   ],
   "text_encoder": [
     "transformers",

safety_checker/config.json

@@ -0,0 +1,168 @@
+{
+  "_commit_hash": "c9ab35ff5f2c362e9e22fbafe278077e196057f0",
+  "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--runwayml--stable-diffusion-v1-5/snapshots/c9ab35ff5f2c362e9e22fbafe278077e196057f0/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": "4.30.1",
+    "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": "4.30.1",
+    "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

@@ -1,20 +1,14 @@
 {
-  "_class_name": "DDIMScheduler",
+  "_class_name": "PNDMScheduler",
   "_diffusers_version": "0.18.0.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": "v_prediction",
-  "rescale_betas_zero_snr": false,
-  "sample_max_value": 1.0,
+  "prediction_type": "epsilon",
   "set_alpha_to_one": false,
   "skip_prk_steps": true,
   "steps_offset": 1,
-  "thresholding": false,
-  "timestep_spacing": "leading",
   "trained_betas": null
 }

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "stabilityai/stable-diffusion-2-1",
+  "_name_or_path": "runwayml/stable-diffusion-v1-5",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -7,19 +7,19 @@
   "bos_token_id": 0,
   "dropout": 0.0,
   "eos_token_id": 2,
-  "hidden_act": "gelu",
-  "hidden_size": 1024,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
   "initializer_factor": 1.0,
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 3072,
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 77,
   "model_type": "clip_text_model",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 23,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 1,
-  "projection_dim": 512,
+  "projection_dim": 768,
   "torch_dtype": "float32",
   "transformers_version": "4.30.1",
-  "vocab_size": 49409
+  "vocab_size": 49408
 }

text_encoder/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd547895b9e7e4cfe392e726896c7789c575cb2feecb1d9921f904141a7b918b
-size 1361684001
+oid sha256:a20d724dacc3f94e73753462567b578a6395b725e17b4ddaeddf0dd3bc148729
+size 492309793

tokenizer/special_tokens_map.json

@@ -13,7 +13,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "!",
+  "pad_token": "<|endoftext|>",
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

unet/config.json

@@ -1,16 +1,11 @@
 {
   "_class_name": "UNet2DConditionModel",
   "_diffusers_version": "0.18.0.dev0",
-  "_name_or_path": "stabilityai/stable-diffusion-2-1",
+  "_name_or_path": "runwayml/stable-diffusion-v1-5",
   "act_fn": "silu",
   "addition_embed_type": null,
   "addition_embed_type_num_heads": 64,
-  "attention_head_dim": [
-    5,
-    10,
-    20,
-    20
-  ],
+  "attention_head_dim": 8,
   "block_out_channels": [
     320,
     640,
@@ -22,7 +17,7 @@
   "class_embeddings_concat": false,
   "conv_in_kernel": 3,
   "conv_out_kernel": 3,
-  "cross_attention_dim": 1024,
+  "cross_attention_dim": 768,
   "cross_attention_norm": null,
   "down_block_types": [
     "CrossAttnDownBlock2D",
@@ -50,7 +45,7 @@
   "resnet_out_scale_factor": 1.0,
   "resnet_skip_time_act": false,
   "resnet_time_scale_shift": "default",
-  "sample_size": 96,
+  "sample_size": 64,
   "time_cond_proj_dim": null,
   "time_embedding_act_fn": null,
   "time_embedding_dim": null,
@@ -62,6 +57,6 @@
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D"
   ],
-  "upcast_attention": true,
-  "use_linear_projection": true
+  "upcast_attention": false,
+  "use_linear_projection": false
 }

unet/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29c7f15709062e790deddc2c6d3d6a3e0a99d4a533b6bfd187bdea64a5e7a961
-size 3463934693
+oid sha256:2f5c8d7a369ce6ca620e1765548ff3ca34567151a93ede69a3fa89fee2a079d2
+size 3438375973

vae/config.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "AutoencoderKL",
   "_diffusers_version": "0.18.0.dev0",
-  "_name_or_path": "stabilityai/stable-diffusion-2-1",
+  "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--runwayml--stable-diffusion-v1-5/snapshots/c9ab35ff5f2c362e9e22fbafe278077e196057f0/vae",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -20,7 +20,7 @@
   "layers_per_block": 2,
   "norm_num_groups": 32,
   "out_channels": 3,
-  "sample_size": 768,
+  "sample_size": 512,
   "scaling_factor": 0.18215,
   "up_block_types": [
     "UpDecoderBlock2D",

vae/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:185b0c03485b4048bb6158de087df301b79ea187844c76ae91cd4cda207282a2
-size 334715569
+oid sha256:c02e0c7c263a4c0630ca3a72380ff55b9e38e0ab41d64dff7bf620a58342bc75
+size 334712113