Upload IMProvPipeline

image_decoder/config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "VQDecoder",
+  "_diffusers_version": "0.24.0",
+  "_name_or_path": "/shared/jiarui/results/video-diffusers/output/mae_p16_text_ed_enc_cat_n1024_arxiv_l400m_224_600k_bs1024x8/amp/hf_pipeline/image_decoder",
+  "codebook_size": 1024,
+  "pixel_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "pixel_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "pretrained_model_name_or_path": "xvjiarui/taming-vq-f16-n1024",
+  "scale_factor": 16
+}

image_decoder/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bb63af4ebfb7c80a9467ede5797276405c27ee00ef5b69f420d6bb04d6531a6
+size 171133028

image_encoder/config.json

@@ -0,0 +1,23 @@
+{
+  "_class_name": "PatchEmbedEncoder",
+  "_diffusers_version": "0.24.0",
+  "_name_or_path": "/shared/jiarui/results/video-diffusers/output/mae_p16_text_ed_enc_cat_n1024_arxiv_l400m_224_600k_bs1024x8/amp/hf_pipeline/image_encoder",
+  "bias": true,
+  "embed_dim": 1024,
+  "height": 224,
+  "in_channels": 3,
+  "layer_norm": false,
+  "patch_size": 16,
+  "pixel_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "pixel_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "scale_factor": 16,
+  "width": 224
+}

image_encoder/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3709e45eba1cec6375dc35a0b676960531bafb6ff34e11ecf08815c5dce72254
+size 3150016

mask_image_model/config.json

@@ -0,0 +1,22 @@
+{
+  "_class_name": "TransformerMAE",
+  "_diffusers_version": "0.24.0",
+  "_name_or_path": "/shared/jiarui/results/video-diffusers/output/mae_p16_text_ed_enc_cat_n1024_arxiv_l400m_224_600k_bs1024x8/amp/hf_pipeline/mask_image_model",
+  "cross_attention_dim": 1024,
+  "decoder_cross_attention": true,
+  "decoder_cross_attention_cat_encoder": true,
+  "decoder_depth": 8,
+  "decoder_embed_dim": 512,
+  "decoder_num_heads": 16,
+  "encoder_cross_attention": true,
+  "encoder_cross_attention_cat_encoder": true,
+  "encoder_depth": 24,
+  "encoder_embed_dim": 1024,
+  "encoder_num_heads": 16,
+  "in_channels": 1024,
+  "in_context_cross_attention": false,
+  "num_embed": null,
+  "out_channels": 1024,
+  "sample_size": 14,
+  "with_cls_token": true
+}

mask_image_model/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff019614e09ba4364300c02065eb009f5352751bc02d7f28558dabc8e519a41a
+size 1772293296

model_index.json

@@ -0,0 +1,29 @@
+{
+  "_class_name": "IMProvPipeline",
+  "_diffusers_version": "0.24.0",
+  "_name_or_path": "/shared/jiarui/results/video-diffusers/output/mae_p16_text_ed_enc_cat_n1024_arxiv_l400m_224_600k_bs1024x8/amp/hf_pipeline",
+  "image_decoder": [
+    "improv.modeling.meta_arch.modules",
+    "VQDecoder"
+  ],
+  "image_encoder": [
+    "improv.modeling.meta_arch.modules",
+    "PatchEmbedEncoder"
+  ],
+  "mask_image_model": [
+    "improv.modeling.meta_arch.modules",
+    "TransformerMAE"
+  ],
+  "scheduler": [
+    "improv.pipelines.pipeline_improv",
+    "MAEScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,5 @@
+{
+  "_class_name": "MAEScheduler",
+  "_diffusers_version": "0.24.0",
+  "schedule": "cosine"
+}

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/shared/jiarui/results/video-diffusers/output/mae_p16_text_ed_enc_cat_n1024_arxiv_l400m_224_600k_bs1024x8/amp/hf_pipeline/text_encoder",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_size": 1024,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 23,
+  "pad_token_id": 1,
+  "projection_dim": 512,
+  "torch_dtype": "float32",
+  "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 sha256:7ec178e5f07ed24deb82bf41fdfde9392c0471755d5bf8d0576b21d7c6dafd46
+size 1361597016

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 +1,34 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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": "/shared/jiarui/results/video-diffusers/output/mae_p16_text_ed_enc_cat_n1024_arxiv_l400m_224_600k_bs1024x8/amp/hf_pipeline/tokenizer",
+  "pad_token": "<|endoftext|>",
+  "special_tokens_map_file": "./special_tokens_map.json",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}