Steps 10k

feature_extractor/preprocessor_config.json

@@ -1,21 +1,4 @@
 {
-  "_valid_processor_keys": [
-    "images",
-    "do_resize",
-    "size",
-    "resample",
-    "do_center_crop",
-    "crop_size",
-    "do_rescale",
-    "rescale_factor",
-    "do_normalize",
-    "image_mean",
-    "image_std",
-    "do_convert_rgb",
-    "return_tensors",
-    "data_format",
-    "input_data_format"
-  ],
   "crop_size": {
     "height": 224,
     "width": 224

logs/text2image-fine-tune/1720731179.088312/events.out.tfevents.1720731179.r-nroggendorff-jupyter-70lo75tp-a759c-9hj3g.2751.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91687d13d3bcb8871f3b2417bc13126db53bf983a14e760e38a40f8002191252
+size 2237

logs/text2image-fine-tune/1720731179.2910058/hparams.yml

@@ -0,0 +1,51 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+cache_dir: null
+caption_column: text
+center_crop: true
+checkpointing_steps: 100000
+checkpoints_total_limit: null
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: nroggendorff/zelda
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+image_column: image
+input_perturbation: 0
+learning_rate: 1.0e-05
+local_rank: -1
+logging_dir: logs
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 1500
+mixed_precision: fp16
+noise_offset: 0
+non_ema_revision: null
+num_train_epochs: 14
+output_dir: sd-zelda-model
+prediction_type: null
+pretrained_model_name_or_path: nroggendorff/animesh
+push_to_hub: false
+random_flip: true
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: null
+snr_gamma: null
+tracker_project_name: text2image-fine-tune
+train_batch_size: 1
+train_data_dir: null
+use_8bit_adam: false
+use_ema: true
+validation_epochs: 5
+variant: null

logs/text2image-fine-tune/events.out.tfevents.1720731179.r-nroggendorff-jupyter-70lo75tp-a759c-9hj3g.2751.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4ea2f3041fba1eb229ac89877fba32e6b43174f5df48cbcd3362e32991f4641
+size 73461

model_index.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "StableDiffusionPipeline",
-  "_diffusers_version": "0.28.0.dev0",
-  "_name_or_path": "runwayml/stable-diffusion-v1-5",
+  "_diffusers_version": "0.30.0.dev0",
+  "_name_or_path": "nroggendorff/animesh",
   "feature_extractor": [
     "transformers",
     "CLIPImageProcessor"
@@ -10,6 +10,11 @@
     null,
     null
   ],
+  "requires_safety_checker": true,
+  "safety_checker": [
+    null,
+    null
+  ],
   "scheduler": [
     "diffusers",
     "PNDMScheduler"

scheduler/scheduler_config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "PNDMScheduler",
-  "_diffusers_version": "0.28.0.dev0",
+  "_diffusers_version": "0.30.0.dev0",
   "beta_end": 0.012,
   "beta_schedule": "scaled_linear",
   "beta_start": 0.00085,

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "runwayml/stable-diffusion-v1-5",
+  "_name_or_path": "nroggendorff/animesh",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -20,6 +20,6 @@
   "pad_token_id": 1,
   "projection_dim": 768,
   "torch_dtype": "float16",
-  "transformers_version": "4.40.1",
+  "transformers_version": "4.42.4",
   "vocab_size": 49408
 }

text_encoder/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd
+oid sha256:4b588d15551213d5e3defc20cb3cc3336f4b9c8990397002e1ed9089584ecf46
 size 246144152

tokenizer/special_tokens_map.json

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

unet/config.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.28.0.dev0",
-  "_name_or_path": "runwayml/stable-diffusion-v1-5",
+  "_diffusers_version": "0.30.0.dev0",
+  "_name_or_path": "nroggendorff/animesh",
   "act_fn": "silu",
   "addition_embed_type": null,
   "addition_embed_type_num_heads": 64,

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:389c0327e81edd5b0ab7a8d633340654e99c7ff92c533428cccfb33762f5c04e
+oid sha256:f301ab1b90332d996b37cdb921431d1cacc01a64340f58753d59dd6285d2372a
 size 3438167536

vae/config.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.28.0.dev0",
-  "_name_or_path": "runwayml/stable-diffusion-v1-5",
+  "_diffusers_version": "0.30.0.dev0",
+  "_name_or_path": "nroggendorff/animesh",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -25,10 +25,13 @@
   "out_channels": 3,
   "sample_size": 512,
   "scaling_factor": 0.18215,
+  "shift_factor": null,
   "up_block_types": [
     "UpDecoderBlock2D",
     "UpDecoderBlock2D",
     "UpDecoderBlock2D",
     "UpDecoderBlock2D"
-  ]
+  ],
+  "use_post_quant_conv": true,
+  "use_quant_conv": true
 }

vae/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fbcf0ebe55a0984f5a5e00d8c4521d52359af7229bb4d81890039d2aa16dd7c
+oid sha256:3e4c08995484ee61270175e9e7a072b66a6e4eeb5f0c266667fe1f45b90daf9a
 size 167335342