Duplicate from williamberman/consistency-decoder

Co-authored-by: Will Berman <williamberman@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,91 @@
+{
+  "_class_name": "ConsistencyDecoderVae",
+  "_diffusers_version": "0.23.0.dev0",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "decoder_args": {
+    "_use_default_values": [
+      "downsample_type",
+      "flip_sin_to_cos",
+      "mid_block_scale_factor",
+      "num_class_embeds",
+      "attention_head_dim",
+      "sample_size",
+      "act_fn",
+      "freq_shift",
+      "class_embed_type",
+      "attn_norm_num_groups",
+      "downsample_padding",
+      "upsample_type",
+      "dropout",
+      "center_input_sample"
+    ],
+    "act_fn": "silu",
+    "add_attention": false,
+    "attention_head_dim": 8,
+    "attn_norm_num_groups": null,
+    "block_out_channels": [
+      320,
+      640,
+      1024,
+      1024
+    ],
+    "center_input_sample": false,
+    "class_embed_type": null,
+    "down_block_types": [
+      "ResnetDownsampleBlock2D",
+      "ResnetDownsampleBlock2D",
+      "ResnetDownsampleBlock2D",
+      "ResnetDownsampleBlock2D"
+    ],
+    "downsample_padding": 1,
+    "downsample_type": "conv",
+    "dropout": 0.0,
+    "flip_sin_to_cos": true,
+    "freq_shift": 0,
+    "in_channels": 7,
+    "layers_per_block": 3,
+    "mid_block_scale_factor": 1,
+    "norm_eps": 1e-05,
+    "norm_num_groups": 32,
+    "num_class_embeds": null,
+    "num_train_timesteps": 1024,
+    "out_channels": 6,
+    "resnet_time_scale_shift": "scale_shift",
+    "sample_size": null,
+    "time_embedding_type": "learned",
+    "up_block_types": [
+      "ResnetUpsampleBlock2D",
+      "ResnetUpsampleBlock2D",
+      "ResnetUpsampleBlock2D",
+      "ResnetUpsampleBlock2D"
+    ],
+    "upsample_type": "conv"
+  },
+  "encoder_args": {
+    "act_fn": "silu",
+    "block_out_channels": [
+      128,
+      256,
+      512,
+      512
+    ],
+    "double_z": true,
+    "down_block_types": [
+      "DownEncoderBlock2D",
+      "DownEncoderBlock2D",
+      "DownEncoderBlock2D",
+      "DownEncoderBlock2D"
+    ],
+    "in_channels": 3,
+    "layers_per_block": 2,
+    "norm_num_groups": 32,
+    "out_channels": 4
+  },
+  "latent_channels": 4,
+  "scaling_factor": 0.18215
+}

diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df6386a06f741c7dfaaa4709b6db39aca345a406d8413dc2c4dbd48a0dce1cfb
+size 1310944884