Upload Kawai Diffusion

model_index.json

@@ -1,9 +1,9 @@
 {
   "_class_name": "StableDiffusionPipeline",
-  "_diffusers_version": "0.10.2",
+  "_diffusers_version": "0.15.0.dev0",
   "feature_extractor": [
     "transformers",
-    "CLIPImageProcessor"
+    "CLIPFeatureExtractor"
   ],
   "requires_safety_checker": true,
   "safety_checker": [
@@ -12,7 +12,7 @@
   ],
   "scheduler": [
     "diffusers",
-    "EulerAncestralDiscreteScheduler"
+    "DDIMScheduler"
   ],
   "text_encoder": [
     "transformers",

scheduler/scheduler_config.json

@@ -1,13 +1,17 @@
 {
-  "_class_name": "EulerAncestralDiscreteScheduler",
-  "_diffusers_version": "0.10.2",
+  "_class_name": "DDIMScheduler",
+  "_diffusers_version": "0.15.0.dev0",
   "beta_end": 0.012,
   "beta_schedule": "scaled_linear",
   "beta_start": 0.00085,
   "clip_sample": false,
+  "clip_sample_range": 1.0,
+  "dynamic_thresholding_ratio": 0.995,
   "num_train_timesteps": 1000,
   "prediction_type": "epsilon",
+  "sample_max_value": 1.0,
   "set_alpha_to_one": false,
   "steps_offset": 1,
+  "thresholding": false,
   "trained_betas": null
 }

text_encoder/config.json

@@ -20,6 +20,6 @@
   "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/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:180c897d4c12afb44895fcb22e6789d1164b1fd2cac65907ea5d34202d59f998
+size 492265874

unet/config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.10.2",
+  "_diffusers_version": "0.15.0.dev0",
   "act_fn": "silu",
   "attention_head_dim": 8,
   "block_out_channels": [
@@ -10,6 +10,9 @@
     1280
   ],
   "center_input_sample": false,
+  "class_embed_type": null,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
   "cross_attention_dim": 768,
   "down_block_types": [
     "CrossAttnDownBlock2D",
@@ -24,12 +27,18 @@
   "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,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_time_scale_shift": "default",
   "sample_size": 64,
+  "time_cond_proj_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
   "up_block_types": [
     "UpBlock2D",
     "CrossAttnUpBlock2D",

unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d13530a9ff30fcf50fdddd32d7f66efe72058358117e13948f843017a907acee
+size 3438167540

vae/config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.10.2",
+  "_diffusers_version": "0.15.0.dev0",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -20,6 +20,7 @@
   "norm_num_groups": 32,
   "out_channels": 3,
   "sample_size": 512,
+  "scaling_factor": 0.18215,
   "up_block_types": [
     "UpDecoderBlock2D",
     "UpDecoderBlock2D",

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a16aadd9501c371b6ef94257a01596e461b13637fd984588175821c77c5a74df
+size 334643276