Upload 52 files

.cache/huggingface/.gitignore

@@ -0,0 +1 @@
+*

.cache/huggingface/download/.gitattributes.metadata

@@ -0,0 +1,3 @@
+ddc9f4aee19e11612a2961f8efc4b3c21d657fcb
+1be3285d360e63aa341c7653e5159dc4c1620bf5
+1742909319.0155773

.cache/huggingface/download/README.md.metadata

@@ -0,0 +1,3 @@
+ddc9f4aee19e11612a2961f8efc4b3c21d657fcb
+31a61f61ce65422385857f1bba6e0e4d3786699f
+1742909318.638954

.cache/huggingface/download/assets/badges/teaser_1.jpg.metadata

@@ -0,0 +1,3 @@
+ddc9f4aee19e11612a2961f8efc4b3c21d657fcb
+6a1d43efb57eb353b9297d1b28bea492773cece14e3ae7fab3e64bea83398b9c
+1742909322.203129

.cache/huggingface/download/assets/badges/teaser_2.jpg.metadata

@@ -0,0 +1,3 @@
+ddc9f4aee19e11612a2961f8efc4b3c21d657fcb
+9e83017175060506c07a8e7f70ab04210c76d55a
+1742909318.7055726

.cache/huggingface/download/feature_extractor/preprocessor_config.json.metadata

@@ -0,0 +1,3 @@
+ddc9f4aee19e11612a2961f8efc4b3c21d657fcb
+c7f2d86b29c96c6db8ae37b12cc51af1b9c7d195
+1742909318.141616

.cache/huggingface/download/model_index.json.metadata

@@ -0,0 +1,3 @@
+ddc9f4aee19e11612a2961f8efc4b3c21d657fcb
+e75bd40ad84047d13345007194f92895873cf82b
+1742909319.634219

.cache/huggingface/download/scheduler/scheduler_config.json.metadata

@@ -0,0 +1,3 @@
+ddc9f4aee19e11612a2961f8efc4b3c21d657fcb
+c30b317c0a1a584a818b79d1d6539132371108c3
+1742909318.6063967

.cache/huggingface/download/text_encoder/config.json.metadata

@@ -0,0 +1,3 @@
+ddc9f4aee19e11612a2961f8efc4b3c21d657fcb
+c04edd53cf2bc5fb23bd5f2b0ed00f77c26d5a94
+1742909318.1476417

.cache/huggingface/download/text_encoder/model.safetensors.metadata

@@ -0,0 +1,3 @@
+ddc9f4aee19e11612a2961f8efc4b3c21d657fcb
+bc1827c465450322616f06dea41596eac7d493f4e95904dcb51f0fc745c4e13f
+1742909350.3445494

.cache/huggingface/download/tokenizer/merges.txt.metadata

@@ -0,0 +1,3 @@
+ddc9f4aee19e11612a2961f8efc4b3c21d657fcb
+76e821f1b6f0a9709293c3b6b51ed90980b3166b
+1742909319.7490191

.cache/huggingface/download/tokenizer/special_tokens_map.json.metadata

@@ -0,0 +1,3 @@
+ddc9f4aee19e11612a2961f8efc4b3c21d657fcb
+ae0c5be6f35217e51c4c000fd325d8de0294e99c
+1742909319.4110515

.cache/huggingface/download/tokenizer/tokenizer_config.json.metadata

@@ -0,0 +1,3 @@
+ddc9f4aee19e11612a2961f8efc4b3c21d657fcb
+bd2abe19377557ff5771584921f9b65fa041fef0
+1742909319.2730854

.cache/huggingface/download/tokenizer/vocab.json.metadata

@@ -0,0 +1,3 @@
+ddc9f4aee19e11612a2961f8efc4b3c21d657fcb
+469be27c5c010538f845f518c4f5e8574c78f7c8
+1742909319.8495104

.cache/huggingface/download/unet/config.json.metadata

@@ -0,0 +1,3 @@
+ddc9f4aee19e11612a2961f8efc4b3c21d657fcb
+d205298974af0e3bf7c79a5ac0a180420ba33dd0
+1742909319.778737

.cache/huggingface/download/unet/diffusion_pytorch_model.safetensors.metadata

@@ -0,0 +1,3 @@
+ddc9f4aee19e11612a2961f8efc4b3c21d657fcb
+ce3346b6b323d484666e614bb23ecfacc0e21ca6aa9ded48b405d4e9f5856528
+1742909561.9789171

.cache/huggingface/download/vae/config.json.metadata

@@ -0,0 +1,3 @@
+ddc9f4aee19e11612a2961f8efc4b3c21d657fcb
+67ee9edc3d8e82f77e046a53423878d4f7649fa8
+1742909319.986227

.cache/huggingface/download/vae/diffusion_pytorch_model.safetensors.metadata

@@ -0,0 +1,3 @@
+ddc9f4aee19e11612a2961f8efc4b3c21d657fcb
+3e4c08995484ee61270175e9e7a072b66a6e4eeb5f0c266667fe1f45b90daf9a
+1742909330.0755255

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* 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
+assets/badges/teaser_1.jpg filter=lfs diff=lfs merge=lfs -text
+assets/badges/pipeline.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,23 @@
+---
+library_name: diffusers
+license: apache-2.0
+pipeline_tag: depth-estimation
+---
+
+# <img src="assets/badges/iris.png" alt="Iris" style="height:1em; vertical-align:bottom;"/> Iris: Bringing Real-World Priors into Diffusion Model for Monocular Depth Estimation
+
+<!-- Provide a quick summary of what the model is/does. -->
+- This model belongs to the family of official Iris models. 
+- This model is trained in disparity space (inverse depth).
+
+
+[![Paper](https://img.shields.io/badge/Project-Website-pink?logo=googlechrome&logoColor=white)](https://arxiv.org/abs/2603.16340)
+[![GitHub](https://img.shields.io/badge/GitHub-Repository-black?logo=github)](https://github.com/NUST-Machine-Intelligence-Laboratory/Iris)
+
+Developed by: 
+[Xinhao Cai](https://strike-1999.github.io/)</span>
+
+![teaser](assets/badges/pipeline.png)
+
+## Usage
+Please refer to this [page](https://github.com/NUST-Machine-Intelligence-Laboratory/Iris). 

feature_extractor/preprocessor_config.json

@@ -0,0 +1,44 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_center_crop",
+    "crop_size",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "do_convert_rgb",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

model_index.json

@@ -0,0 +1,38 @@
+{
+  "_class_name": "DirectRegressionPipeline",
+  "_diffusers_version": "0.28.0.dev0",
+  "_name_or_path": "stabilityai/stable-diffusion-2-base",
+  "feature_extractor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "image_encoder": [
+    null,
+    null
+  ],
+  "requires_safety_checker": false,
+  "safety_checker": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "PNDMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,15 @@
+{
+  "_class_name": "PNDMScheduler",
+  "_diffusers_version": "0.28.0.dev0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "timestep_spacing": "leading",
+  "trained_betas": null
+}

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "stabilityai/stable-diffusion-2-base",
+  "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": "4.40.1",
+  "vocab_size": 49408
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc1827c465450322616f06dea41596eac7d493f4e95904dcb51f0fc745c4e13f
+size 680820392

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 +1,38 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "!",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "!",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}

unet/config.json

@@ -0,0 +1,73 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.32.2",
+  "_name_or_path": "/home/caixinhao/Lotus/pretrained_models/jingheya/lotus-depth-d-v2-0-disparity",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": [
+    5,
+    10,
+    20,
+    20
+  ],
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": "projection",
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 1024,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dropout": 0.0,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "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,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 4,
+  "projection_class_embeddings_input_dim": 4,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": 64,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "transformer_layers_per_block": 1,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": true
+}

unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dac6b77256db8d8fe35cb2e4b88d13bfd16b269eebe2b1310e9292e191ca4470
+size 3470311272