End of training

model_index.json

@@ -1,27 +1,21 @@
 {
-  "_class_name": "StableDiffusionInstructPix2PixPipeline",
+  "_class_name": "FlaxStableDiffusionPipeline",
   "_diffusers_version": "0.28.0.dev0",
-  "_name_or_path": "runwayml/stable-diffusion-v1-5",
   "feature_extractor": [
     "transformers",
     "CLIPImageProcessor"
   ],
-  "image_encoder": [
-    null,
-    null
-  ],
-  "requires_safety_checker": true,
   "safety_checker": [
     "stable_diffusion",
-    "StableDiffusionSafetyChecker"
+    "FlaxStableDiffusionSafetyChecker"
   ],
   "scheduler": [
     "diffusers",
-    "PNDMScheduler"
+    "FlaxPNDMScheduler"
   ],
   "text_encoder": [
     "transformers",
-    "CLIPTextModel"
+    "FlaxCLIPTextModel"
   ],
   "tokenizer": [
     "transformers",
@@ -29,10 +23,10 @@
   ],
   "unet": [
     "diffusers",
-    "UNet2DConditionModel"
+    "FlaxUNet2DConditionModel"
   ],
   "vae": [
     "diffusers",
-    "AutoencoderKL"
+    "FlaxAutoencoderKL"
   ]
 }

safety_checker/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/root/.cache/huggingface/hub/models--runwayml--stable-diffusion-v1-5/snapshots/1d0c4ebf6ff58a5caecab40fa1406526bca4b5b9/safety_checker",
+  "_name_or_path": "clip-vit-large-patch14/",
   "architectures": [
     "StableDiffusionSafetyChecker"
   ],
@@ -15,7 +15,7 @@
     "num_attention_heads": 12
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.40.0",
+  "transformers_version": "4.41.2",
   "vision_config": {
     "dropout": 0.0,
     "hidden_size": 1024,

safety_checker/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:851a10d6a89e86dfac8397af9e09f754b6220dfa71a334c3a60c7883149e748c
+size 1215939995

scheduler/scheduler_config.json

@@ -1,15 +1,13 @@
 {
-  "_class_name": "PNDMScheduler",
+  "_class_name": "FlaxPNDMScheduler",
   "_diffusers_version": "0.28.0.dev0",
   "beta_end": 0.012,
   "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,
-  "timestep_spacing": "leading",
+  "steps_offset": 0,
   "trained_betas": null
 }

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "runwayml/stable-diffusion-v1-5",
+  "_name_or_path": "openai/clip-vit-large-patch14",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -19,7 +19,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 1,
   "projection_dim": 768,
-  "torch_dtype": "float16",
-  "transformers_version": "4.40.0",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
   "vocab_size": 49408
 }

text_encoder/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38aca8345bad31819530d6291463fe6b38b07275ae38065f774b30e7a8e07d64
+size 246127918

unet/config.json

@@ -1,5 +1,5 @@
 {
-  "_class_name": "UNet2DConditionModel",
+  "_class_name": "FlaxUNet2DConditionModel",
   "_diffusers_version": "0.28.0.dev0",
   "_name_or_path": "runwayml/stable-diffusion-v1-5",
   "act_fn": "silu",
@@ -51,6 +51,7 @@
   "resnet_time_scale_shift": "default",
   "reverse_transformer_layers_per_block": null,
   "sample_size": 64,
+  "split_head_dim": false,
   "time_cond_proj_dim": null,
   "time_embedding_act_fn": null,
   "time_embedding_dim": null,
@@ -64,5 +65,6 @@
     "CrossAttnUpBlock2D"
   ],
   "upcast_attention": false,
-  "use_linear_projection": false
+  "use_linear_projection": false,
+  "use_memory_efficient_attention": false
 }

unet/diffusion_flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dde0f0048a971823b359c6c191b8ffc41fe67e7f3642de3d580ae1a80b38a60c
+size 3438154451

vae/config.json

@@ -1,7 +1,6 @@
 {
-  "_class_name": "AutoencoderKL",
+  "_class_name": "FlaxAutoencoderKL",
   "_diffusers_version": "0.28.0.dev0",
-  "_name_or_path": "runwayml/stable-diffusion-v1-5",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -15,15 +14,12 @@
     "DownEncoderBlock2D",
     "DownEncoderBlock2D"
   ],
-  "force_upcast": true,
   "in_channels": 3,
   "latent_channels": 4,
-  "latents_mean": null,
-  "latents_std": null,
   "layers_per_block": 2,
   "norm_num_groups": 32,
   "out_channels": 3,
-  "sample_size": 512,
+  "sample_size": 256,
   "scaling_factor": 0.18215,
   "up_block_types": [
     "UpDecoderBlock2D",

vae/diffusion_flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e3e81680c6669960f086eca278c8a1f89dd2ed7eadef806e049b56e426c1809
+size 167316369