End of training

README.md

@@ -1,7 +1,7 @@
 
 ---
 license: creativeml-openrail-m
-base_model: stabilityai/stable-diffusion-2-depth
+base_model: runwayml/stable-diffusion-v1-5
 tags:
 - stable-diffusion
 - stable-diffusion-diffusers
@@ -12,6 +12,6 @@ inference: true
 ---
     
 # Textual inversion text2image fine-tuning - AACEE/textual_inversion_cat
-These are textual inversion adaption weights for stabilityai/stable-diffusion-2-depth. You can find some example images in the following. 
+These are textual inversion adaption weights for runwayml/stable-diffusion-v1-5. You can find some example images in the following. 
 
 

checkpoint-1000/optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f86107b4fae79babbda76a4f1f28f0871fe74061b6505ca87376b5815a43e793
-size 404760109
+oid sha256:351260f9eb6c37331bb93da4b923f31019d967d148cddfc62ef789b72954b2f1
+size 303570477

checkpoint-1000/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f5c3a29639ba45e9cea80e829cb9e442f4b059a5033d9abbbefdc3234a4bfe7
-size 1361701921
+oid sha256:6fe1e0e9d12a24a0019693fe8790beef23c239b7edd1875004cdc9f38346ba1a
+size 492322337

checkpoint-1000/random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88f3bb4d20d1d2e810e3d88154f83592d8ff470e0a6db2f699f4663fea4ba8fd
+oid sha256:2d04ca35edc3dac6f0ff0e7d1e6ce7d6abfb4632dc1380d6d1fb38d1f71e174b
 size 14663

checkpoint-1500/optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5433aff1ae19cffcfb35c4ce0d9e6038fced4350f3fe109998a969bedef7b8f
-size 404760109
+oid sha256:8ebaf5197d3c7bbb6f4a165003ca16dc7bf30186f5cc2437b8eae23b49d0758b
+size 303570477

checkpoint-1500/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81bb851115dc65c73cbd2a4c30baec1a92efeae22931204aeb929af8257ac2ff
-size 1361701921
+oid sha256:cb5b2b01c3c8c84b515092139e18aa7be2f6615d53505783cef9a4eb6ad19ddf
+size 492322337

checkpoint-1500/random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2eb603eeb1ffbdf46ca43ad8cd7af0d588867c15334ec708a756177883184837
-size 14663
+oid sha256:1ab04c972b749c68cedd2a6fd9d6a1dd2a3353065765360cfb802ab298f84d5d
+size 14727

checkpoint-2000/optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e47e26afdd664980dc8c3b3c7e22f49606e6505bcc24479bc6f9bfa39b0d08a
-size 404760109
+oid sha256:421563e73a9e470eabb6f7877cb0a45817116607c001eed744b8b10851698221
+size 303570477

checkpoint-2000/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d25d8b63c506d2c289849c7921e481c3c2b001413794ebb94693f706651f6a3
-size 1361701921
+oid sha256:cd91ff223221672b82f568b2e3059c68462545264d528ff64efba81da6b759b9
+size 492322337

checkpoint-2000/random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09024fcad3c189f1565aed8dc000207537b737c972bd54b6da0b21e114126e66
+oid sha256:4ecab6d2acd5606f567fda54d15453618b2abddb038aa49cefe22b0291e77217
 size 14663

checkpoint-2500/optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a035b7cbc9fa0465daf98dbff4522d762e7dc9f5868ff73d1dd69e3ce85b217
-size 404760109
+oid sha256:e0fa1259f49efd84d1c2dd56633d4f2cf20f5fe42aa3d6d39e888ab86894e34a
+size 303570477

checkpoint-2500/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae23aeb245d00a4cd115f7d0eec3b6bc93742defa8a94dedb9e72fd861cc87dc
-size 1361701921
+oid sha256:a8734d41b742d86d32569fdbb8da2f92353647fc9d612671f5bbd8b3f57780fd
+size 492322337

checkpoint-2500/random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f088557d2036ef06daf20def625f4b7c9026d9cac4b17eed2db5cd9830595fce
-size 14727
+oid sha256:1dc0d16b7010dc42ce5c93c096adc4ead54e6b0f1464f5270a2f19e9fb448709
+size 14663

checkpoint-3000/optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:609e7e77fb6906c9504c2195c6d819ffbc08f591f827ae1b998eb70f5d124e94
-size 404760109
+oid sha256:8fe173af645c8c2c2862f13333d1d98c5ddb347a5913b65614cb1a357ae72499
+size 303570477

checkpoint-3000/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72dfe01f47cf61ec0c0ff81ff7327cc9d224181f8cb8eaa9c06f850f56deda88
-size 1361701921
+oid sha256:24d175faa3f1c86a0a7b62cfd79d9a9017dc6ea61b9fecc632e9a9a8bfb1896a
+size 492322337

checkpoint-3000/random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f04b250949009e36eb1b4f73a9c82a2a60986bd58753c7dc302395e3eb62f78a
+oid sha256:a82bc1e1947519d800c1f320658d46afda7bf0a26d0343f28cfa87187dd8fc13
 size 14727

checkpoint-500/optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ba32327b0d5a791fcdb66ccc879fee4f3be13bf250b92929f59b240cd5d65ad
-size 404760109
+oid sha256:0ec90a82888971b2e52bb87f2159f6c9b118b5d6e4b4326ead303a73bfba27f3
+size 303570477

checkpoint-500/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5254d8bfbf746625a2635ae9e4bbde62c8522450b94fc8c79c6a5f43a931b799
-size 1361701921
+oid sha256:dfb0b9705f781a508523f48be8dcb685e03eaac67ddcd358942e05b25e6e13b8
+size 492322337

checkpoint-500/random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca9d7278da13f4ad233aea006bf58d2980d264f7e42a4965459c92f8f95ad27e
+oid sha256:7b605ad814bed7e0ba6347aa0fcdf330c324a5d95a70c92710b7430e39aa580c
 size 14663

feature_extractor/preprocessor_config.json

@@ -1,24 +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,
-  "ensure_multiple_of": 1,
+  "feature_extractor_type": "CLIPFeatureExtractor",
   "image_mean": [
-    0.5,
-    0.5,
-    0.5
+    0.48145466,
+    0.4578275,
+    0.40821073
   ],
-  "image_processor_type": "DPTImageProcessor",
+  "image_processor_type": "CLIPImageProcessor",
   "image_std": [
-    0.5,
-    0.5,
-    0.5
+    0.26862954,
+    0.26130258,
+    0.27577711
   ],
-  "keep_aspect_ratio": false,
-  "resample": 2,
+  "resample": 3,
   "rescale_factor": 0.00392156862745098,
   "size": {
-    "height": 384,
-    "width": 384
+    "shortest_edge": 224
   }
 }

learned_embeds-steps-1000.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71eec6a979cde290edab32752c97eea135e8bb560ced2f6e5470c917cdea6b16
-size 5025
+oid sha256:3e3bfc7f75c1b62d8343b31a8c749d0e2fbff20fae548970b5a195524d558ddf
+size 4001

learned_embeds-steps-1500.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96a24ad42e46a9c1e283834f3bc3c4c4b00319fab8ee99a259aaf681f1a93caf
-size 5025
+oid sha256:a748badcfca34e770012d55d9532e6e490e414cd7f4a49d8889540d3320b9655
+size 4001

learned_embeds-steps-2000.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a97333e59cc70bcec2a16b6987991dedbf723e1240844ec951a1d0912a1e18fe
-size 5025
+oid sha256:d45604154ae99357b5808c7fe99ae8a4a6e5ef4e032d0c34c8e45c0a87de2c8d
+size 4001

learned_embeds-steps-2500.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb9a5e491b784d75e03f936aac03ccb047a247a1c8eb1a5e7818433bfa1b956f
-size 5025
+oid sha256:b5fdda7de54b9629579e69a009e4800248edb03f98cc4db011fe3c2fbe753276
+size 4001

learned_embeds-steps-3000.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5228ad0effeb42c5b1276e7a0abf979d79444979ececa432eedb31ec9e34ebec
-size 5025
+oid sha256:fce8b54f9440a566f570137ffdd4cc2a9646cf53dc5ef65de4be96355401d9f6
+size 4001

learned_embeds-steps-500.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d41dd636426fcad891e9890d89f17900e0e4ab6d46e756ca9959e2ef9e239bb
-size 5022
+oid sha256:83da42705a3c6a99f5a62c15ffaa5a92569d8dfe8f7ed0f4ee59c5431318fac8
+size 3998

learned_embeds.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b83d87d8cd415a974691112b178320823fceb0e33c63ac8ad7cdf4b6bc4738a
-size 4864
+oid sha256:b942244a753c8029b2b307b3bc320aadbf4409d3132ad7737a86f9a02f29af18
+size 3840

logs/textual_inversion/1689107596.745057/events.out.tfevents.1689107596.p4de-st-p4de24xlarge-564.3414741.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ae232439c86bc6b38dff25a050eb997239725a1aaf56c9d890c8dc725f89132
+size 2260

logs/textual_inversion/1689107596.7586236/hparams.yml

@@ -0,0 +1,46 @@
+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: toy
+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: 20
+num_validation_images: 4
+num_vectors: 1
+output_dir: textual_inversion_cat
+placeholder_token: <cat-toy>
+pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
+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: ./cat
+validation_epochs: null
+validation_prompt: null
+validation_steps: 100

logs/textual_inversion/events.out.tfevents.1689107596.p4de-st-p4de24xlarge-564.3414741.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a927eb916203cfe3636aa102fb753ea9baa81b96cacf37ca94e885681a0a095
+size 1007054

model_index.json

@@ -3,12 +3,12 @@
   "_diffusers_version": "0.18.1",
   "feature_extractor": [
     "transformers",
-    "DPTImageProcessor"
+    "CLIPImageProcessor"
   ],
   "requires_safety_checker": true,
   "safety_checker": [
-    null,
-    null
+    "stable_diffusion",
+    "StableDiffusionSafetyChecker"
   ],
   "scheduler": [
     "diffusers",

safety_checker/config.json

@@ -0,0 +1,168 @@
+{
+  "_commit_hash": "c9ab35ff5f2c362e9e22fbafe278077e196057f0",
+  "_name_or_path": "/data/home/ancao/.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": "4.30.2",
+    "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": "4.30.2",
+    "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

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "stabilityai/stable-diffusion-2-depth",
+  "_name_or_path": "runwayml/stable-diffusion-v1-5",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -7,18 +7,18 @@
   "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": "4.30.2",
   "vocab_size": 49409

text_encoder/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c0b6afab6fdb9ecef989a674eb2d4a23f31ca6115c0583d1b6b1ec3e8af53ee
-size 1361684001
+oid sha256:17f5de19a430ba6a420445ac5fd5c9a59804da12f68bfaff3a6aa7a6056e9bdb
+size 492312865

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

@@ -1,17 +1,12 @@
 {
   "_class_name": "UNet2DConditionModel",
   "_diffusers_version": "0.18.1",
-  "_name_or_path": "stabilityai/stable-diffusion-2-depth",
+  "_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": [
-    5,
-    10,
-    20,
-    20
-  ],
+  "attention_head_dim": 8,
   "block_out_channels": [
     320,
     640,
@@ -23,7 +18,7 @@
   "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",
@@ -37,7 +32,7 @@
   "encoder_hid_dim_type": null,
   "flip_sin_to_cos": true,
   "freq_shift": 0,
-  "in_channels": 5,
+  "in_channels": 4,
   "layers_per_block": 2,
   "mid_block_only_cross_attention": null,
   "mid_block_scale_factor": 1,
@@ -52,7 +47,7 @@
   "resnet_out_scale_factor": 1.0,
   "resnet_skip_time_act": false,
   "resnet_time_scale_shift": "default",
-  "sample_size": 32,
+  "sample_size": 64,
   "time_cond_proj_dim": null,
   "time_embedding_act_fn": null,
   "time_embedding_dim": null,
@@ -66,5 +61,5 @@
     "CrossAttnUpBlock2D"
   ],
   "upcast_attention": false,
-  "use_linear_projection": true
+  "use_linear_projection": false
 }

unet/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87e1d440b0aca6f6e4590d30495a59c920fdb40419f5c9bf82dcd47b5bf21016
-size 3463946213
+oid sha256:39aeb5f57e936fdb52331f49d69299fb130a5456c269b67c08699b109e8485fd
+size 3438375973

vae/config.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "AutoencoderKL",
   "_diffusers_version": "0.18.1",
-  "_name_or_path": "stabilityai/stable-diffusion-2-depth",
+  "_name_or_path": "runwayml/stable-diffusion-v1-5",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -20,7 +20,7 @@
   "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.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:185b0c03485b4048bb6158de087df301b79ea187844c76ae91cd4cda207282a2
+oid sha256:11a6fc35e77a2d5696ae6a494f797f01b7ab97b08b5f8f2f17e19d0ef169b1ca
 size 334715569