new model

feature_extractor/preprocessor_config.json

@@ -14,7 +14,7 @@
     0.4578275,
     0.40821073
   ],
-  "image_processor_type": "CLIPImageProcessor",
+  "image_processor_type": "CLIPFeatureExtractor",
   "image_std": [
     0.26862954,
     0.26130258,

model_index.json

@@ -1,9 +1,9 @@
 {
   "_class_name": "FlaxStableDiffusionPipeline",
-  "_diffusers_version": "0.12.0.dev0",
+  "_diffusers_version": "0.15.0.dev0",
   "feature_extractor": [
     "transformers",
-    "CLIPImageProcessor"
+    "CLIPFeatureExtractor"
   ],
   "safety_checker": [
     null,

scheduler/scheduler_config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "FlaxPNDMScheduler",
-  "_diffusers_version": "0.12.0.dev0",
+  "_diffusers_version": "0.15.0.dev0",
   "beta_end": 0.012,
   "beta_schedule": "scaled_linear",
   "beta_start": 0.00085,

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/root/sd15",
+  "_name_or_path": "openai/clip-vit-large-patch14",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -13,13 +13,13 @@
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 200,
+  "max_position_embeddings": 77,
   "model_type": "clip_text_model",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "pad_token_id": 1,
   "projection_dim": 768,
   "torch_dtype": "float32",
-  "transformers_version": "4.25.1",
+  "transformers_version": "4.26.1",
   "vocab_size": 49408
 }

text_encoder/flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91f67bccdc24594ce7f212e3ba7cbc2707cec54b44f399e4bb0e4e6d167ee2fe
-size 492626539
+oid sha256:29a525735ff64ea971fdd682fd91fa4ea3496783cf72c9c20ae4df25c788388d
+size 492248682

tokenizer/tokenizer_config.json

@@ -18,8 +18,8 @@
     "single_word": false
   },
   "errors": "replace",
-  "model_max_length": 200,
-  "name_or_path": "/root/sd15-flax/",
+  "model_max_length": 77,
+  "name_or_path": "/home/user/project-fur/e6_dump/stable-diffusion-v1-5-flax/",
   "pad_token": "<|endoftext|>",
   "special_tokens_map_file": "./special_tokens_map.json",
   "tokenizer_class": "CLIPTokenizer",

unet/config.json

@@ -1,7 +1,6 @@
 {
   "_class_name": "FlaxUNet2DConditionModel",
-  "_diffusers_version": "0.12.0.dev0",
-  "_name_or_path": "/root/.cache/huggingface/diffusers/models--runwayml--stable-diffusion-v1-5/snapshots/39593d5650112b4cc580433f6b0435385882d819/unet",
+  "_diffusers_version": "0.15.0.dev0",
   "act_fn": "silu",
   "attention_head_dim": 8,
   "block_out_channels": [
@@ -11,7 +10,6 @@
     1280
   ],
   "center_input_sample": false,
-  "class_embed_type": null,
   "cross_attention_dim": 768,
   "down_block_types": [
     "CrossAttnDownBlock2D",
@@ -21,19 +19,15 @@
   ],
   "downsample_padding": 1,
   "dropout": 0.0,
-  "dual_cross_attention": false,
   "flip_sin_to_cos": true,
   "freq_shift": 0,
   "in_channels": 4,
   "layers_per_block": 2,
   "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,
-  "resnet_time_scale_shift": "default",
   "sample_size": 64,
   "up_block_types": [
     "UpBlock2D",
@@ -41,6 +35,6 @@
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D"
   ],
-  "upcast_attention": false,
-  "use_linear_projection": false
+  "use_linear_projection": false,
+  "use_memory_efficient": false
 }

unet/diffusion_flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89c29cbdf7f1f7c805067b8de6aad7877ab7dcef36d7b453013dd89005060aa3
+oid sha256:17dbabeb41ea6668b53fdb48eec83728749cfc747ba7bec0b4b19fd0bedf5abc
 size 3438108367

vae/config.json

@@ -1,7 +1,6 @@
 {
   "_class_name": "FlaxAutoencoderKL",
-  "_diffusers_version": "0.12.0.dev0",
-  "_name_or_path": "/root/.cache/huggingface/diffusers/models--runwayml--stable-diffusion-v1-5/snapshots/39593d5650112b4cc580433f6b0435385882d819/vae",
+  "_diffusers_version": "0.15.0.dev0",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -21,6 +20,7 @@
   "norm_num_groups": 32,
   "out_channels": 3,
   "sample_size": 512,
+  "scaling_factor": 0.18215,
   "up_block_types": [
     "UpDecoderBlock2D",
     "UpDecoderBlock2D",