test with konosuba model

feature_extractor/preprocessor_config.json

@@ -0,0 +1,20 @@
+{
+  "crop_size": 224,
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "size": 224
+}

model_index.json

@@ -1,18 +1,17 @@
 {
   "_class_name": "StableDiffusionPipeline",
-  "_diffusers_version": "0.10.2",
+  "_diffusers_version": "0.6.0",
   "feature_extractor": [
-    null,
-    null
+    "transformers",
+    "CLIPFeatureExtractor"
   ],
-  "requires_safety_checker": null,
   "safety_checker": [
-    null,
-    null
+    "stable_diffusion",
+    "StableDiffusionSafetyChecker"
   ],
   "scheduler": [
     "diffusers",
-    "DDPMScheduler"
+    "PNDMScheduler"
   ],
   "text_encoder": [
     "transformers",

safety_checker/config.json

@@ -0,0 +1,174 @@
+{
+  "_name_or_path": "CompVis/stable-diffusion-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,
+    "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,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": 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": "4.21.0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vocab_size": 49408
+  },
+  "text_config_dict": {
+    "hidden_size": 768,
+    "intermediate_size": 3072,
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12
+  },
+  "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,
+    "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,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": 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": "4.21.0",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "vision_config_dict": {
+    "hidden_size": 1024,
+    "intermediate_size": 4096,
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14
+  }
+}

safety_checker/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:193490b58ef62739077262e833bf091c66c29488058681ac25cf7df3d8190974
+size 1216061799

scheduler/scheduler_config.json

@@ -1,14 +1,12 @@
 {
-  "_class_name": "DDPMScheduler",
-  "_diffusers_version": "0.10.2",
+  "_class_name": "PNDMScheduler",
+  "_diffusers_version": "0.6.0",
   "beta_end": 0.012,
-  "beta_schedule": "linear",
+  "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,
-  "trained_betas": null,
-  "variance_type": "fixed_small"
+  "trained_betas": null
 }

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "logs\\MyneFactoryBase_20230203-010401\\ckpts\\last-MyneFactoryBase-ep19-gs115520",
+  "_name_or_path": "openai/clip-vit-large-patch14",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -20,6 +20,6 @@
   "pad_token_id": 1,
   "projection_dim": 768,
   "torch_dtype": "float32",
-  "transformers_version": "4.25.1",
+  "transformers_version": "4.21.0",
   "vocab_size": 49408
 }

text_encoder/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d8898ffbfae0b20762baee0ebbe664d79ed6ebdb1fff17dc55ca5527526007c
-size 492308087
+oid sha256:389532dada8efa38871eb92d2f8366a927b1b8ea4fd6a7215d23d834c51c80d3
+size 492305335

tokenizer/tokenizer_config.json

@@ -19,7 +19,7 @@
   },
   "errors": "replace",
   "model_max_length": 77,
-  "name_or_path": "logs\\MyneFactoryBase_20230203-010401\\ckpts\\last-MyneFactoryBase-ep19-gs115520",
+  "name_or_path": "openai/clip-vit-large-patch14",
   "pad_token": "<|endoftext|>",
   "special_tokens_map_file": "./special_tokens_map.json",
   "tokenizer_class": "CLIPTokenizer",
@@ -30,6 +30,5 @@
     "normalized": true,
     "rstrip": false,
     "single_word": false
-  },
-  "use_fast": false
+  }
 }

unet/config.json

@@ -1,7 +1,6 @@
 {
   "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.10.2",
-  "_name_or_path": "logs\\MyneFactoryBase_20230203-010401\\ckpts\\last-MyneFactoryBase-ep19-gs115520",
+  "_diffusers_version": "0.6.0",
   "act_fn": "silu",
   "attention_head_dim": 8,
   "block_out_channels": [
@@ -19,7 +18,6 @@
     "DownBlock2D"
   ],
   "downsample_padding": 1,
-  "dual_cross_attention": false,
   "flip_sin_to_cos": true,
   "freq_shift": 0,
   "in_channels": 4,
@@ -27,16 +25,12 @@
   "mid_block_scale_factor": 1,
   "norm_eps": 1e-05,
   "norm_num_groups": 32,
-  "num_class_embeds": null,
-  "only_cross_attention": false,
   "out_channels": 4,
-  "sample_size": 96,
+  "sample_size": 32,
   "up_block_types": [
     "UpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D"
-  ],
-  "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:dcfdc45fd2ed4d8b31f51faa909baf96f58d5942038c267f47603850468445bf
-size 3438364325
+oid sha256:c2c820f9b296154e60d6581c0bbd62cf95845f0ab2004e36e9ef3faf39a55ae3
+size 3438354725

vae/config.json

@@ -1,7 +1,6 @@
 {
   "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.10.2",
-  "_name_or_path": "logs\\MyneFactoryBase_20230203-010401\\ckpts\\last-MyneFactoryBase-ep19-gs115520",
+  "_diffusers_version": "0.6.0",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -20,7 +19,7 @@
   "layers_per_block": 2,
   "norm_num_groups": 32,
   "out_channels": 3,
-  "sample_size": 768,
+  "sample_size": 256,
   "up_block_types": [
     "UpDecoderBlock2D",
     "UpDecoderBlock2D",

vae/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15a996c812c0e5b1a5c5815ab0192244c9876e073a6eda3b576b204a968167c3
-size 167402961
+oid sha256:6e20f5df1c5196f0caa2f777d2ed840f5517f5775f98c38bd6595c31aaea40c3
+size 334707217