Change to pytorch

model_index.json

@@ -1,21 +1,22 @@
 {
-  "_class_name": "FlaxStableDiffusionPipeline",
-  "_diffusers_version": "0.12.1",
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.16.1",
   "feature_extractor": [
     "transformers",
     "CLIPFeatureExtractor"
   ],
+  "requires_safety_checker": true,
   "safety_checker": [
-    "stable_diffusion",
-    "FlaxStableDiffusionSafetyChecker"
+    null,
+    null
   ],
   "scheduler": [
     "diffusers",
-    "FlaxPNDMScheduler"
+    "PNDMScheduler"
   ],
   "text_encoder": [
     "transformers",
-    "FlaxCLIPTextModel"
+    "CLIPTextModel"
   ],
   "tokenizer": [
     "transformers",
@@ -23,10 +24,10 @@
   ],
   "unet": [
     "diffusers",
-    "FlaxUNet2DConditionModel"
+    "UNet2DConditionModel"
   ],
   "vae": [
     "diffusers",
-    "FlaxAutoencoderKL"
+    "AutoencoderKL"
   ]
 }

safety_checker/config.json

@@ -1,168 +0,0 @@
-{
-  "_commit_hash": "770db1b8bf37fb2af64431813923984d569032b6",
-  "_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,
-    "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": "4.28.1",
-    "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": "4.28.1",
-    "typical_p": 1.0,
-    "use_bfloat16": false
-  }
-}

scheduler/scheduler_config.json

@@ -1,6 +1,6 @@
 {
-  "_class_name": "FlaxPNDMScheduler",
-  "_diffusers_version": "0.12.1",
+  "_class_name": "PNDMScheduler",
+  "_diffusers_version": "0.16.1",
   "beta_end": 0.012,
   "beta_schedule": "scaled_linear",
   "beta_start": 0.00085,

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "openai/clip-vit-large-patch14",
+  "_name_or_path": "ddpo-aesthetic/text_encoder",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -20,6 +20,6 @@
   "pad_token_id": 1,
   "projection_dim": 768,
   "torch_dtype": "float32",
-  "transformers_version": "4.28.1",
+  "transformers_version": "4.29.2",
   "vocab_size": 49408
 }

vae/diffusion_flax_model.msgpack → text_encoder/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed39fc57b0224dec2c0cc6f9a532633ccef89815e40b544a6b8f38f422023d8a
-size 334623853
+oid sha256:98124f3d5663b2f14ff08d4c29db93800622b4fcfa3d952bb6f9112f5d6dadd7
+size 492307041

unet/config.json

@@ -1,6 +1,10 @@
 {
-  "_class_name": "FlaxUNet2DConditionModel",
-  "_diffusers_version": "0.12.1",
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.16.1",
+  "_name_or_path": "ddpo-aesthetic/unet",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
   "attention_head_dim": 8,
   "block_out_channels": [
     320,
@@ -8,26 +12,52 @@
     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": 768,
+  "cross_attention_norm": null,
   "down_block_types": [
     "CrossAttnDownBlock2D",
     "CrossAttnDownBlock2D",
     "CrossAttnDownBlock2D",
     "DownBlock2D"
   ],
+  "downsample_padding": 1,
   "dropout": 0.0,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
   "flip_sin_to_cos": true,
   "freq_shift": 0,
   "in_channels": 4,
   "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_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": 64,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
   "up_block_types": [
     "UpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D"
   ],
-  "use_linear_projection": false
+  "upcast_attention": false,
+  "use_linear_projection": false,
+  "use_memory_efficient_attention": false
 }

unet/diffusion_flax_model.msgpack

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f905b3dd417b8fa53898d48bc164165e3382241b05585c7bfc8a88cb0ab942af
-size 3438108367

safety_checker/flax_model.msgpack → unet/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b337b0d044f66ad64979018685377ef49a2433ee1bd7357bcc11c9389139a7d6
-size 1215939995
+oid sha256:86d0144fa1a0d535ebc458d492e8ab69653db4734b2d3c6880f2a1c6e067b49f
+size 3438366373

vae/config.json

@@ -1,6 +1,7 @@
 {
-  "_class_name": "FlaxAutoencoderKL",
-  "_diffusers_version": "0.12.1",
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.16.1",
+  "_name_or_path": "ddpo-aesthetic/vae",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -20,6 +21,7 @@
   "norm_num_groups": 32,
   "out_channels": 3,
   "sample_size": 256,
+  "scaling_factor": 0.18215,
   "up_block_types": [
     "UpDecoderBlock2D",
     "UpDecoderBlock2D",

text_encoder/flax_model.msgpack → vae/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8059e504aa3ccf6853510c6a2d44d21dc1783a102395f54026c77cc5fada641e
-size 492248682
+oid sha256:af27ea858349760ebe3311953e0bfe8d6fd257dc9537ae0b2b938c262132a2c6
+size 334711857