Upload folder using huggingface_hub

model_index.json

@@ -0,0 +1,21 @@
+{
+  "_class_name": "OMSPipeline",
+  "_diffusers_version": "0.23.1",
+  "_name_or_path": "oms_b_openclip_15",
+  "oms_module": [
+    "unet_2d_condition_woct",
+    "UNet2DConditionWoCTModel"
+  ],
+  "oms_text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "oms_tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "sd_pipeline": [
+    "stable_diffusion",
+    "StableDiffusionPipeline"
+  ]
+}

oms_module/config.json

@@ -0,0 +1,51 @@
+{
+  "_class_name": "UNet2DConditionWoCTModel",
+  "_diffusers_version": "0.23.1",
+  "_name_or_path": "h1t/oms_b_openclip_15_21",
+  "subfolder": "oms_module",
+  "act_fn": "silu",
+  "attention_head_dim": [
+    5,
+    10,
+    20
+  ],
+  "block_out_channels": [
+    160,
+    320,
+    640
+  ],
+  "center_input_sample": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 1024,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "DownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "only_cross_attention": false,
+  "out_channels": 4,
+  "resnet_out_scale_factor": 1.0,
+  "sample_size": null,
+  "transformer_layers_per_block": 1,
+  "up_block_types": [
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "UpBlock2D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": false
+}

oms_module/diffusion_pytorch_model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b10f84b1947e7e767b1d2166fbd4259bbf269235bdae31ae4a394dab8c45e30
+size 308083816

oms_text_encoder/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "stabilityai/stable-diffusion-2-1",
+  "subfolder": "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": "float16",
+  "transformers_version": "4.32.1",
+  "vocab_size": 49408
+}

oms_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
+    },
+    "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": "stabilityai/stable-diffusion-2-1-base",
+    "subfolder": "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
+    }
+  }