Upload folder using huggingface_hub

marigold_appearance/finetuned/.gitattributes

@@ -0,0 +1,36 @@
+*.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
+doc/teaser_collage_transparant.png filter=lfs diff=lfs merge=lfs -text

marigold_appearance/finetuned/README.md

@@ -0,0 +1,82 @@
+---
+license: openrail++
+language:
+- en
+pipeline_tag: other
+pinned: true
+tags:
+- intrinsic-decomposition
+- intrinsic decomposition
+- image analysis
+- computer vision
+- in-the-wild
+- zero-shot
+---
+
+<h1 align="center">Marigold Intrinsic Image Decomposition (IID) Appearance v1-1 Model Card</h1>
+
+<p align="center">
+<a title="Image IID" href="https://huggingface.co/spaces/prs-eth/marigold-iid" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
+    <img src="https://img.shields.io/badge/%F0%9F%A4%97%20Image%20IID%20-Demo-yellow" alt="Image IID">
+</a>
+<a title="diffusers" href="https://huggingface.co/docs/diffusers/using-diffusers/marigold_usage" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
+    <img src="https://img.shields.io/badge/%F0%9F%A4%97%20diffusers%20-Integration%20🧨-yellow" alt="diffusers">
+</a>
+<a title="Github" href="https://github.com/prs-eth/marigold" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
+    <img src="https://img.shields.io/github/stars/prs-eth/marigold?label=GitHub%20%E2%98%85&logo=github&color=C8C" alt="Github">
+</a>
+<a title="Website" href="https://marigoldcomputervision.github.io/" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
+    <img src="https://img.shields.io/badge/%E2%99%A5%20Project%20-Website-blue" alt="Website">
+</a>
+<a title="arXiv" href="https://arxiv.org/abs/2312.02145" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
+    <img src="https://img.shields.io/badge/%F0%9F%93%84%20Read%20-Paper-AF3436" alt="arXiv">
+</a>
+<a title="Social" href="https://twitter.com/antonobukhov1" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
+    <img src="https://img.shields.io/twitter/follow/:?label=Subscribe%20for%20updates!" alt="Social">
+</a>
+<a title="License" href="https://huggingface.co/stabilityai/stable-diffusion-2/blob/main/LICENSE-MODEL" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
+    <img src="https://img.shields.io/badge/License-OpenRAIL++-929292" alt="License">
+</a>
+</p>
+
+This is a model card for the `marigold-iid-appearance-v1-1` model for single-image Intrinsic Image Decomposition (IID). 
+The model is fine-tuned from the `stable-diffusion-2` [model](https://huggingface.co/stabilityai/stable-diffusion-2) as 
+described in 
+<span style="color:red;">a follow-up of our [CVPR'2024 paper](https://arxiv.org/abs/2312.02145) titled "Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation".</span>
+
+This model type (`appearance`) is trained to perform InteriorVerse decomposition into **Albedo** and two **BRDF material** properties: **roughness** and **metallicity**.
+Both the input image and the output albedo are in the sRGB color space.
+For an alternative model type (`lighting`) that performs decomposition into Albedo, Diffuse shading, and Non-diffuse residual, click 
+[here](https://huggingface.co/prs-eth/marigold-iid-lighting-v1-1).
+
+- Play with the interactive [Hugging Face Spaces demo](https://huggingface.co/spaces/prs-eth/marigold-iid): check out how the model works with example images or upload your own.
+- Use it with [diffusers](https://huggingface.co/docs/diffusers/using-diffusers/marigold_usage) to compute the results with a few lines of code.
+- Get to the bottom of things with our [official codebase](https://github.com/prs-eth/marigold).
+
+## Model Details
+- **Developed by:** [Bingxin Ke](http://www.kebingxin.com/), [Kevin Qu](https://ch.linkedin.com/in/kevin-qu-b3417621b), [Tianfu Wang](https://tianfwang.github.io/), [Nando Metzger](https://nandometzger.github.io/), [Shengyu Huang](https://shengyuh.github.io/), [Bo Li](https://www.linkedin.com/in/bobboli0202), [Anton Obukhov](https://www.obukhov.ai/), [Konrad Schindler](https://scholar.google.com/citations?user=FZuNgqIAAAAJ).
+- **Model type:** Generative latent diffusion-based intrinsic image decomposition (appearance: albedo, roughness, and metallicity) from a single image.
+- **Language:** English.
+- **License:** [CreativeML Open RAIL++-M License](https://huggingface.co/stabilityai/stable-diffusion-2/blob/main/LICENSE-MODEL).
+- **Model Description:** This model can be used to generate an estimated intrinsic image decomposition of an input image. 
+  - **Resolution**: Even though any resolution can be processed, the model inherits the base diffusion model's effective resolution of roughly **768** pixels. 
+    This means that for optimal predictions, any larger input image should be resized to make the longer side 768 pixels before feeding it into the model.
+  - **Steps and scheduler**: This model was designed for usage with **DDIM** scheduler and between **1 and 50** denoising steps.
+  - **Outputs**:
+    - **Albedo**: The predicted values are between 0 and 1, sRGB space.
+    - **Roughness and metallicity**: The predicted values are between 0 and 1, linear space.
+    - **Uncertainty maps**: Produced for each modality only when multiple predictions are ensembled with ensemble size larger than 2.
+- **Resources for more information:** [Project Website](https://marigoldcomputervision.github.io/), [Paper](https://arxiv.org/abs/2312.02145), [Code](https://github.com/prs-eth/marigold).
+- **Cite as:**
+
+
+<span style="color:red;">Placeholder for the citation block of the follow-up paper</span>
+
+```bibtex
+@InProceedings{ke2023repurposing,
+      title={Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation},
+      author={Bingxin Ke and Anton Obukhov and Shengyu Huang and Nando Metzger and Rodrigo Caye Daudt and Konrad Schindler},
+      booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
+      year={2024}
+}
+```

marigold_appearance/finetuned/model_index.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "StableDiffusionAOVMatEstPipeline",
+  "_diffusers_version": "0.20.2",
+  "_name_or_path": "./models/stable-diffusion-2-1",
+  "target_properties": {
+    "target_names": [
+      "albedo"
+    ],
+    "albedo": {
+      "prediction_space": "srgb"
+    }
+  },
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

marigold_appearance/finetuned/scheduler/scheduler_config.json

@@ -0,0 +1,20 @@
+{
+  "_class_name": "DDIMScheduler",
+  "_diffusers_version": "0.35.1",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "clip_sample_range": 1.0,
+  "dynamic_thresholding_ratio": 0.995,
+  "num_train_timesteps": 1000,
+  "prediction_type": "v_prediction",
+  "rescale_betas_zero_snr": true,
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "thresholding": false,
+  "timestep_spacing": "trailing",
+  "trained_betas": null
+}

marigold_appearance/finetuned/text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "hf-models/stable-diffusion-v2-768x768/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": "4.25.0.dev0",
+  "vocab_size": 49408
+}

marigold_appearance/finetuned/text_encoder/model.fp16.safetensors

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

marigold_appearance/finetuned/text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e4aa519f64dc6386f88221a66c106a09fa027b47a20cc0e126687695f2a6669
+size 1361597016

marigold_appearance/finetuned/text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9c787e9388134c1a25dc69934a51a32a2683b38b8a9b017e1f3a692b8ed6b98
+size 1361679905

marigold_appearance/finetuned/text_encoder/pytorch_model.fp16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfc767ee894a2d26166aa7c22b7b297a1ff8e246493734490dd048087d4c9c07
+size 680899947

marigold_appearance/finetuned/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
+  }
+}

marigold_appearance/finetuned/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|>"
+}

marigold_appearance/finetuned/unet/config.json

@@ -0,0 +1,73 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.35.1",
+  "_name_or_path": "./model_appearance_finetuned/stable-diffusion-2/unet",
+  "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": null,
+  "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": 8,
+  "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": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": 96,
+  "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
+}

marigold_appearance/finetuned/unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf735761e4134d52dd28df3b0906b72f61be59f74ca4e7b865552e3032d8e585
+size 3463772592

marigold_appearance/finetuned/vae/config.json

@@ -0,0 +1,34 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.8.0",
+  "_name_or_path": "hf-models/stable-diffusion-v2-768x768/vae",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 4,
+  "latents_mean": null,
+  "latents_std": null,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 768,
+  "scaling_factor": 0.18215,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

marigold_appearance/finetuned/vae/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4302e1efa25f3a47ceb7536bc335715ad9d1f203e90c2d25507600d74006e89
+size 334715313

marigold_appearance/finetuned/vae/diffusion_pytorch_model.fp16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44915add42092106e70bffac475aae4283b5e8167a8a0c5f55ccc667ee4ebeb5
+size 167405651

marigold_appearance/finetuned/vae/diffusion_pytorch_model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e4c08995484ee61270175e9e7a072b66a6e4eeb5f0c266667fe1f45b90daf9a
+size 167335342

marigold_appearance/finetuned/vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1d993488569e928462932c8c38a0760b874d166399b14414135bd9c42df5815
+size 334643276

marigold_appearance/pretrained/.gitattributes

@@ -0,0 +1,36 @@
+*.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
+doc/teaser_collage_transparant.png filter=lfs diff=lfs merge=lfs -text

marigold_appearance/pretrained/README.md

@@ -0,0 +1,82 @@
+---
+license: openrail++
+language:
+- en
+pipeline_tag: other
+pinned: true
+tags:
+- intrinsic-decomposition
+- intrinsic decomposition
+- image analysis
+- computer vision
+- in-the-wild
+- zero-shot
+---
+
+<h1 align="center">Marigold Intrinsic Image Decomposition (IID) Appearance v1-1 Model Card</h1>
+
+<p align="center">
+<a title="Image IID" href="https://huggingface.co/spaces/prs-eth/marigold-iid" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
+    <img src="https://img.shields.io/badge/%F0%9F%A4%97%20Image%20IID%20-Demo-yellow" alt="Image IID">
+</a>
+<a title="diffusers" href="https://huggingface.co/docs/diffusers/using-diffusers/marigold_usage" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
+    <img src="https://img.shields.io/badge/%F0%9F%A4%97%20diffusers%20-Integration%20🧨-yellow" alt="diffusers">
+</a>
+<a title="Github" href="https://github.com/prs-eth/marigold" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
+    <img src="https://img.shields.io/github/stars/prs-eth/marigold?label=GitHub%20%E2%98%85&logo=github&color=C8C" alt="Github">
+</a>
+<a title="Website" href="https://marigoldcomputervision.github.io/" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
+    <img src="https://img.shields.io/badge/%E2%99%A5%20Project%20-Website-blue" alt="Website">
+</a>
+<a title="arXiv" href="https://arxiv.org/abs/2312.02145" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
+    <img src="https://img.shields.io/badge/%F0%9F%93%84%20Read%20-Paper-AF3436" alt="arXiv">
+</a>
+<a title="Social" href="https://twitter.com/antonobukhov1" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
+    <img src="https://img.shields.io/twitter/follow/:?label=Subscribe%20for%20updates!" alt="Social">
+</a>
+<a title="License" href="https://huggingface.co/stabilityai/stable-diffusion-2/blob/main/LICENSE-MODEL" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
+    <img src="https://img.shields.io/badge/License-OpenRAIL++-929292" alt="License">
+</a>
+</p>
+
+This is a model card for the `marigold-iid-appearance-v1-1` model for single-image Intrinsic Image Decomposition (IID). 
+The model is fine-tuned from the `stable-diffusion-2` [model](https://huggingface.co/stabilityai/stable-diffusion-2) as 
+described in 
+<span style="color:red;">a follow-up of our [CVPR'2024 paper](https://arxiv.org/abs/2312.02145) titled "Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation".</span>
+
+This model type (`appearance`) is trained to perform InteriorVerse decomposition into **Albedo** and two **BRDF material** properties: **roughness** and **metallicity**.
+Both the input image and the output albedo are in the sRGB color space.
+For an alternative model type (`lighting`) that performs decomposition into Albedo, Diffuse shading, and Non-diffuse residual, click 
+[here](https://huggingface.co/prs-eth/marigold-iid-lighting-v1-1).
+
+- Play with the interactive [Hugging Face Spaces demo](https://huggingface.co/spaces/prs-eth/marigold-iid): check out how the model works with example images or upload your own.
+- Use it with [diffusers](https://huggingface.co/docs/diffusers/using-diffusers/marigold_usage) to compute the results with a few lines of code.
+- Get to the bottom of things with our [official codebase](https://github.com/prs-eth/marigold).
+
+## Model Details
+- **Developed by:** [Bingxin Ke](http://www.kebingxin.com/), [Kevin Qu](https://ch.linkedin.com/in/kevin-qu-b3417621b), [Tianfu Wang](https://tianfwang.github.io/), [Nando Metzger](https://nandometzger.github.io/), [Shengyu Huang](https://shengyuh.github.io/), [Bo Li](https://www.linkedin.com/in/bobboli0202), [Anton Obukhov](https://www.obukhov.ai/), [Konrad Schindler](https://scholar.google.com/citations?user=FZuNgqIAAAAJ).
+- **Model type:** Generative latent diffusion-based intrinsic image decomposition (appearance: albedo, roughness, and metallicity) from a single image.
+- **Language:** English.
+- **License:** [CreativeML Open RAIL++-M License](https://huggingface.co/stabilityai/stable-diffusion-2/blob/main/LICENSE-MODEL).
+- **Model Description:** This model can be used to generate an estimated intrinsic image decomposition of an input image. 
+  - **Resolution**: Even though any resolution can be processed, the model inherits the base diffusion model's effective resolution of roughly **768** pixels. 
+    This means that for optimal predictions, any larger input image should be resized to make the longer side 768 pixels before feeding it into the model.
+  - **Steps and scheduler**: This model was designed for usage with **DDIM** scheduler and between **1 and 50** denoising steps.
+  - **Outputs**:
+    - **Albedo**: The predicted values are between 0 and 1, sRGB space.
+    - **Roughness and metallicity**: The predicted values are between 0 and 1, linear space.
+    - **Uncertainty maps**: Produced for each modality only when multiple predictions are ensembled with ensemble size larger than 2.
+- **Resources for more information:** [Project Website](https://marigoldcomputervision.github.io/), [Paper](https://arxiv.org/abs/2312.02145), [Code](https://github.com/prs-eth/marigold).
+- **Cite as:**
+
+
+<span style="color:red;">Placeholder for the citation block of the follow-up paper</span>
+
+```bibtex
+@InProceedings{ke2023repurposing,
+      title={Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation},
+      author={Bingxin Ke and Anton Obukhov and Shengyu Huang and Nando Metzger and Rodrigo Caye Daudt and Konrad Schindler},
+      booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
+      year={2024}
+}
+```

marigold_appearance/pretrained/model_index.json

@@ -0,0 +1,52 @@
+{
+  "_class_name": "MarigoldIntrinsicsPipeline",
+  "_diffusers_version": "0.24.0",
+  "prediction_type": "intrinsics",
+  "default_denoising_steps": 4,
+  "default_processing_resolution": 768,
+  "target_properties": {
+    "target_names": [
+      "albedo",
+      "material"
+    ],
+    "albedo": {
+      "prediction_space": "srgb"
+    },
+    "material": {
+      "prediction_space": "stack",
+      "sub_target_names": [
+        "roughness",
+        "metallicity",
+        null
+      ]
+    },
+    "roughness": {
+      "prediction_space": "linear",
+      "up_to_scale": false
+    },
+    "metallicity": {
+      "prediction_space": "linear",
+      "up_to_scale": false
+    }
+  },
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ],
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ]
+}

marigold_appearance/pretrained/scheduler/scheduler_config.json

@@ -0,0 +1,20 @@
+{
+  "_class_name": "DDIMScheduler",
+  "_diffusers_version": "0.27.2",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "clip_sample_range": 1.0,
+  "dynamic_thresholding_ratio": 0.995,
+  "num_train_timesteps": 1000,
+  "prediction_type": "v_prediction",
+  "rescale_betas_zero_snr": true,
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "thresholding": false,
+  "timestep_spacing": "trailing",
+  "trained_betas": null
+}

marigold_appearance/pretrained/text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "hf-models/stable-diffusion-v2-768x768/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": "4.25.0.dev0",
+  "vocab_size": 49408
+}

marigold_appearance/pretrained/text_encoder/model.fp16.safetensors

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

marigold_appearance/pretrained/text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e4aa519f64dc6386f88221a66c106a09fa027b47a20cc0e126687695f2a6669
+size 1361597016

marigold_appearance/pretrained/text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9c787e9388134c1a25dc69934a51a32a2683b38b8a9b017e1f3a692b8ed6b98
+size 1361679905

marigold_appearance/pretrained/text_encoder/pytorch_model.fp16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfc767ee894a2d26166aa7c22b7b297a1ff8e246493734490dd048087d4c9c07
+size 680899947

marigold_appearance/pretrained/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
+  }
+}

marigold_appearance/pretrained/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|>"
+}

marigold_appearance/pretrained/unet/config.json

@@ -0,0 +1,72 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.20.1",
+  "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": null,
+  "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": 12,
+  "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": 8,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": 96,
+  "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
+}

marigold_appearance/pretrained/unet/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28c55e17780d2a94f05d0930953b65eb633b12e1ab73d96bfbd56c42d854df57
+size 3464063333

marigold_appearance/pretrained/unet/diffusion_pytorch_model.fp16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcc12337003d89bfb838dea857b4234de80fd8d33e21b8270bfdd6d92b424a34
+size 1732176213

marigold_appearance/pretrained/unet/diffusion_pytorch_model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c7ab00d751edc8ac26a56d6d5bdcef600f2577b7ec708bea9cbac3fb12eda39
+size 1731973872

marigold_appearance/pretrained/unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c38ae47ce50376e66cc89f61a8a78c4b2e0d00349db650dbe5048b94c83412b
+size 3463864784

marigold_appearance/pretrained/vae/config.json

@@ -0,0 +1,34 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.8.0",
+  "_name_or_path": "hf-models/stable-diffusion-v2-768x768/vae",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 4,
+  "latents_mean": null,
+  "latents_std": null,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 768,
+  "scaling_factor": 0.18215,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

marigold_appearance/pretrained/vae/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4302e1efa25f3a47ceb7536bc335715ad9d1f203e90c2d25507600d74006e89
+size 334715313

marigold_appearance/pretrained/vae/diffusion_pytorch_model.fp16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44915add42092106e70bffac475aae4283b5e8167a8a0c5f55ccc667ee4ebeb5
+size 167405651

marigold_appearance/pretrained/vae/diffusion_pytorch_model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e4c08995484ee61270175e9e7a072b66a6e4eeb5f0c266667fe1f45b90daf9a
+size 167335342

marigold_appearance/pretrained/vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1d993488569e928462932c8c38a0760b874d166399b14414135bd9c42df5815
+size 334643276

marigold_lighting/finetuned/.gitattributes

@@ -0,0 +1,4 @@
+unet/diffusion_pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+unet/diffusion_pytorch_model.fp16.bin filter=lfs diff=lfs merge=lfs -text
+unet/diffusion_pytorch_model.fp16.safetensors filter=lfs diff=lfs merge=lfs -text
+unet/diffusion_pytorch_model.safetensors filter=lfs diff=lfs merge=lfs -text

marigold_lighting/finetuned/README.md

@@ -0,0 +1,86 @@
+---
+license: openrail++
+language:
+- en
+pipeline_tag: other
+pinned: true
+tags:
+- intrinsic-decomposition
+- intrinsic decomposition
+- image analysis
+- computer vision
+- in-the-wild
+- zero-shot
+---
+
+<h1 align="center">Marigold Intrinsic Image Decomposition (IID) Lighting v1-1 Model Card</h1>
+
+<p align="center">
+<a title="Image IID" href="https://huggingface.co/spaces/prs-eth/marigold-iid" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
+    <img src="https://img.shields.io/badge/%F0%9F%A4%97%20Image%20IID%20-Demo-yellow" alt="Image IID">
+</a>
+<a title="diffusers" href="https://huggingface.co/docs/diffusers/using-diffusers/marigold_usage" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
+    <img src="https://img.shields.io/badge/%F0%9F%A4%97%20diffusers%20-Integration%20🧨-yellow" alt="diffusers">
+</a>
+<a title="Github" href="https://github.com/prs-eth/marigold" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
+    <img src="https://img.shields.io/github/stars/prs-eth/marigold?label=GitHub%20%E2%98%85&logo=github&color=C8C" alt="Github">
+</a>
+<a title="Website" href="https://marigoldcomputervision.github.io/" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
+    <img src="https://img.shields.io/badge/%E2%99%A5%20Project%20-Website-blue" alt="Website">
+</a>
+<a title="arXiv" href="https://arxiv.org/abs/2312.02145" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
+    <img src="https://img.shields.io/badge/%F0%9F%93%84%20Read%20-Paper-AF3436" alt="arXiv">
+</a>
+<a title="Social" href="https://twitter.com/antonobukhov1" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
+    <img src="https://img.shields.io/twitter/follow/:?label=Subscribe%20for%20updates!" alt="Social">
+</a>
+<a title="License" href="https://huggingface.co/stabilityai/stable-diffusion-2/blob/main/LICENSE-MODEL" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
+    <img src="https://img.shields.io/badge/License-OpenRAIL++-929292" alt="License">
+</a>
+</p>
+
+This is a model card for the `marigold-iid-lighting-v1-1` model for single-image Intrinsic Image Decomposition (IID). 
+The model is fine-tuned from the `stable-diffusion-2` [model](https://huggingface.co/stabilityai/stable-diffusion-2) as 
+described in 
+<span style="color:red;">a follow-up of our [CVPR'2024 paper](https://arxiv.org/abs/2312.02145) titled "Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation".</span>
+
+This model type (`lighting`) is trained to perform HyperSim decomposition into **Albedo**, **Diffuse shading**, and **Non-diffuse residual**.
+This decomposition aligns with the intrinsic residual model \\(I = A*S+R\\), where the image \\(I\\) is composed of 
+a three-channel albedo \\(A\\), a three-channel diffuse shading component \\(S\\) (representing illumination color), 
+and an additive three-channel residual term \\(R\\) capturing non-diffuse effects.
+The input is in the sRGB color space, while all outputs are in linear space.
+For an alternative model type (`appearance`) that performs decomposition into Albedo, Roughness, and Metallicity, click 
+[here](https://huggingface.co/prs-eth/marigold-iid-appearance-v1-1).
+
+- Play with the interactive [Hugging Face Spaces demo](https://huggingface.co/spaces/prs-eth/marigold-iid): check out how the model works with example images or upload your own.
+- Use it with [diffusers](https://huggingface.co/docs/diffusers/using-diffusers/marigold_usage) to compute the results with a few lines of code.
+- Get to the bottom of things with our [official codebase](https://github.com/prs-eth/marigold).
+
+## Model Details
+- **Developed by:** [Bingxin Ke](http://www.kebingxin.com/), [Kevin Qu](https://ch.linkedin.com/in/kevin-qu-b3417621b), [Tianfu Wang](https://tianfwang.github.io/), [Nando Metzger](https://nandometzger.github.io/), [Shengyu Huang](https://shengyuh.github.io/), [Bo Li](https://www.linkedin.com/in/bobboli0202), [Anton Obukhov](https://www.obukhov.ai/), [Konrad Schindler](https://scholar.google.com/citations?user=FZuNgqIAAAAJ).
+- **Model type:** Generative latent diffusion-based intrinsic image decomposition (lighting: albedo, diffuse shading, and non-diffuse residual) from a single image.
+- **Language:** English.
+- **License:** [CreativeML Open RAIL++-M License](https://huggingface.co/stabilityai/stable-diffusion-2/blob/main/LICENSE-MODEL).
+- **Model Description:** This model can be used to generate an estimated intrinsic image decomposition of an input image. 
+  - **Resolution**: Even though any resolution can be processed, the model inherits the base diffusion model's effective resolution of roughly **768** pixels. 
+    This means that for optimal predictions, any larger input image should be resized to make the longer side 768 pixels before feeding it into the model.
+  - **Steps and scheduler**: This model was designed for usage with **DDIM** scheduler and between **1 and 50** denoising steps.
+  - **Outputs**:
+    - **Albedo**: The predicted values are between 0 and 1, linear space.
+    - **Diffuse shading**: The predicted values are between 0 and 1, linear space.
+    - **Non-diffuse residual**: The predicted values are between 0 and 1, linear space.
+    - **Uncertainty maps**: Produced for each modality only when multiple predictions are ensembled with ensemble size larger than 2.
+- **Resources for more information:** [Project Website](https://marigoldcomputervision.github.io/), [Paper](https://arxiv.org/abs/2312.02145), [Code](https://github.com/prs-eth/marigold).
+- **Cite as:**
+
+
+<span style="color:red;">Placeholder for the citation block of the follow-up paper</span>
+
+```bibtex
+@InProceedings{ke2023repurposing,
+      title={Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation},
+      author={Bingxin Ke and Anton Obukhov and Shengyu Huang and Nando Metzger and Rodrigo Caye Daudt and Konrad Schindler},
+      booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
+      year={2024}
+}
+```

marigold_lighting/finetuned/gitattributes

@@ -0,0 +1,36 @@
+*.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
+doc/teaser_collage_transparant.png filter=lfs diff=lfs merge=lfs -text

marigold_lighting/finetuned/model_index.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "StableDiffusionAOVMatEstPipeline",
+  "_diffusers_version": "0.20.2",
+  "_name_or_path": "./models/stable-diffusion-2-1",
+  "target_properties": {
+    "target_names": [
+      "albedo"
+    ],
+    "albedo": {
+      "prediction_space": "srgb"
+    }
+  },
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

marigold_lighting/finetuned/scheduler/scheduler_config.json

@@ -0,0 +1,20 @@
+{
+  "_class_name": "DDIMScheduler",
+  "_diffusers_version": "0.35.1",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "clip_sample_range": 1.0,
+  "dynamic_thresholding_ratio": 0.995,
+  "num_train_timesteps": 1000,
+  "prediction_type": "v_prediction",
+  "rescale_betas_zero_snr": true,
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "thresholding": false,
+  "timestep_spacing": "trailing",
+  "trained_betas": null
+}

marigold_lighting/finetuned/text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "hf-models/stable-diffusion-v2-768x768/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": "4.25.0.dev0",
+  "vocab_size": 49408
+}

marigold_lighting/finetuned/text_encoder/model.fp16.safetensors

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