upload model

model_index.json

@@ -0,0 +1,24 @@
+{
+  "_class_name": "VQDiffusionPipeline",
+  "_diffusers_version": "0.7.0.dev0",
+  "scheduler": [
+    "diffusers",
+    "VQDiffusionScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "transformer": [
+    "diffusers",
+    "Transformer2DModel"
+  ],
+  "vqvae": [
+    "diffusers",
+    "VQModel"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,10 @@
+{
+  "_class_name": "VQDiffusionScheduler",
+  "_diffusers_version": "0.7.0.dev0",
+  "a_cumulative_end": 9e-06,
+  "a_cumulative_start": 0.99999,
+  "c_cumulative_end": 0.99999,
+  "c_cumulative_start": 9e-06,
+  "num_embed": 4097,
+  "num_train_timesteps": 100
+}

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "openai/clip-vit-base-patch32",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 512,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "projection_dim": 512,
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0.dev0",
+  "vocab_size": 49408
+}

text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31a10531e4683c8ddeb5aa700586f1ed6074d1db99e82f612250f8f035d0fb38
+size 252727223

tokenizer/special_tokens_map.json

@@ -0,0 +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
+  }
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "device_map": "auto",
+  "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": "openai/clip-vit-base-patch32",
+  "pad_token": "!",
+  "special_tokens_map_file": "/home/patrick_huggingface_co/.cache/huggingface/hub/models--openai--clip-vit-base-patch32/snapshots/e6a30b603a447e251fdaca1c3056b2a16cdfebeb/special_tokens_map.json",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

transformer/config.json

@@ -0,0 +1,28 @@
+{
+  "_class_name": "Transformer2DModel",
+  "_diffusers_version": "0.7.0.dev0",
+  "attention_bias": true,
+  "context_dim": 512,
+  "d_head": 88,
+  "depth": 36,
+  "discrete": true,
+  "dropout": 0.0,
+  "ff_layers": [
+    "Linear",
+    "ApproximateGELU",
+    "Linear",
+    "Dropout"
+  ],
+  "height": 32,
+  "in_channels": null,
+  "n_heads": 16,
+  "norm_layers": [
+    "AdaLayerNorm",
+    "AdaLayerNorm",
+    "LayerNorm"
+  ],
+  "num_embed": 4097,
+  "num_embeds_ada_norm": 100,
+  "num_groups": 32,
+  "width": 32
+}

transformer/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b4f3633099b4dcf09ff0187cee3eb6ff3f918fd4f7d1a3dede87ef831b2f277
+size 5437498090

vqvae/config.json

@@ -0,0 +1,31 @@
+{
+  "_class_name": "VQModel",
+  "_diffusers_version": "0.7.0.dev0",
+  "act_fn": "silu",
+  "block_out_channels": [
+    64,
+    128,
+    256,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "AttnDownEncoderBlock2D"
+  ],
+  "e_dim": 128,
+  "in_channels": 3,
+  "latent_channels": 256,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "num_vq_embeddings": 4096,
+  "out_channels": 3,
+  "sample_size": 32,
+  "up_block_types": [
+    "AttnUpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

vqvae/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4a66f084d7c7d2041a9b330de89043974d09024e2d151d960a8c6e982c82d29
+size 256154659