Migrate model to PyTorch

model_index.json

@@ -1,5 +1,5 @@
 {
-  "_class_name": "FlaxStableDiffusionPipeline",
+  "_class_name": "StableDiffusionPipeline",
   "_diffusers_version": "0.16.0.dev0",
   "feature_extractor": [
     null,
@@ -11,11 +11,11 @@
   ],
   "scheduler": [
     "diffusers",
-    "FlaxPNDMScheduler"
+    "PNDMScheduler"
   ],
   "text_encoder": [
     "transformers",
-    "FlaxCLIPTextModel"
+    "CLIPTextModel"
   ],
   "tokenizer": [
     "transformers",
@@ -23,10 +23,10 @@
   ],
   "unet": [
     "diffusers",
-    "FlaxUNet2DConditionModel"
+    "UNet2DConditionModel"
   ],
   "vae": [
     "diffusers",
-    "FlaxAutoencoderKL"
+    "AutoencoderKL"
   ]
 }

scheduler/scheduler_config.json

@@ -1,5 +1,5 @@
 {
-  "_class_name": "FlaxPNDMScheduler",
+  "_class_name": "PNDMScheduler",
   "_diffusers_version": "0.16.0.dev0",
   "beta_end": 0.012,
   "beta_schedule": "scaled_linear",

text_encoder/{flax_model.msgpack → pytorch_model.bin}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60f914bf080600a7d6678c70339679c7997d03faec449d2bd2e5269673b25762
-size 1361564130
+oid sha256:2188379b05015f531d61503e714234d00a64939792f3098b324e516547f0194f
+size 1361674657

tokenizer/special_tokens_map.json

@@ -1,24 +1,24 @@
 {
-    "bos_token": {
-      "content": "<|startoftext|>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false
-    },
-    "eos_token": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false
-    },
-    "pad_token": "!",
-    "unk_token": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false
-    }
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "!",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
   }
+}

tokenizer/tokenizer_config.json

@@ -1,34 +1,34 @@
 {
-    "add_prefix_space": false,
-    "bos_token": {
-      "__type": "AddedToken",
-      "content": "<|startoftext|>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false
-    },
-    "do_lower_case": true,
-    "eos_token": {
-      "__type": "AddedToken",
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false
-    },
-    "errors": "replace",
-    "model_max_length": 77,
-    "name_or_path": "stabilityai/stable-diffusion-2",
-    "pad_token": "<|endoftext|>",
-    "special_tokens_map_file": "./special_tokens_map.json",
-    "tokenizer_class": "CLIPTokenizer",
-    "unk_token": {
-      "__type": "AddedToken",
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false
-    }
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 77,
+  "name_or_path": "stabilityai/stable-diffusion-2"
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
   }
+}

unet/config.json

@@ -1,5 +1,5 @@
 {
-  "_class_name": "FlaxUNet2DConditionModel",
+  "_class_name": "UNet2DConditionModel",
   "_diffusers_version": "0.16.0.dev0",
   "act_fn": "silu",
   "attention_head_dim": [
@@ -15,7 +15,12 @@
     1280
   ],
   "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
   "cross_attention_dim": 1024,
+  "cross_attention_norm": null,
   "down_block_types": [
     "CrossAttnDownBlock2D",
     "CrossAttnDownBlock2D",
@@ -25,23 +30,35 @@
   "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_type": "positional",
+  "timestep_post_act": null,
   "up_block_types": [
     "UpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D"
   ],
+  "upcast_attention": false,
   "use_linear_projection": true,
   "use_memory_efficient_attention": false
 }

unet/{diffusion_flax_model.msgpack → diffusion_pytorch_model.bin}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f165b465f6925fe41aa1f6578bf17e5f54974d8be63785d53fb66a25da915c84
-size 3463667343
+oid sha256:65b425b483ab603699a9d9948759ed18a200d207852ffd2f26f640d0c22507c5
+size 3463925093

vae/config.json

@@ -1,5 +1,5 @@
 {
-  "_class_name": "FlaxAutoencoderKL",
+  "_class_name": "AutoencoderKL",
   "_diffusers_version": "0.16.0.dev0",
   "act_fn": "silu",
   "block_out_channels": [

vae/{diffusion_flax_model.msgpack → diffusion_pytorch_model.bin}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f45517affbc93f169d2f5022c6c7d6c7912477f571e8011ddddeca115001562
-size 334623853
+oid sha256:36bb8e1b54aba3a0914eb35fba13dcb107e9f18d379d1df2158732cd4bf56a94
+size 334711857