Upload 12 files

ComfyUI/models/transparent-background/InSPyReNet_Clothing_latest4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2203e1966c00efa5536f718bac00897eb805b28e102145617642d1ae267cd979
+size 367521044

ComfyUI/models/transparent-background/InSPyReNet_SwinB_DIS5K.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac057287c91e89e994f9b94906ea6154899546266640ed675843fb941b1ffc77
+size 367520613

ComfyUI/models/transparent-background/InSPyReNet_SwinB_HU.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3462148fec1189c57a5e81ce24c9e5e33e3e37fa9b7dce99a51dd827cb0bae6
+size 367526592

ComfyUI/models/transparent-background/InSPyReNet_SwinB_Plus_Ultra.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a6fe2a73ab0532d6d0b8d82849a9760a226df719e3063d09b4149ece6f80fcd
+size 367520613

ComfyUI/models/transparent-background/ckpt_base.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a6fe2a73ab0532d6d0b8d82849a9760a226df719e3063d09b4149ece6f80fcd
+size 367520613

ComfyUI/models/transparent-background/ckpt_base_nightly.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86b896ce80988f5cae1a401746e621c8389e177e03c667e2ad493c1f84b8dbd4
+size 367520613

ComfyUI/models/transparent-background/ckpt_fast.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e61ed7e85763dd83a796e1d650ea78604fff524121750858c54a6b560ac58c82
+size 367520613

ComfyUI/models/vitmatte/README.md

@@ -0,0 +1,42 @@
+---
+license: apache-2.0
+tags:
+- vision
+---
+
+# ViTMatte model
+
+ViTMatte model trained on Composition-1k. It was introduced in the paper [ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers](https://arxiv.org/abs/2305.15272) by Yao et al. and first released in [this repository](https://github.com/hustvl/ViTMatte). 
+
+Disclaimer: The team releasing ViTMatte did not write a model card for this model so this model card has been written by the Hugging Face team.
+
+## Model description
+
+ViTMatte is a simple approach to image matting, the task of accurately estimating the foreground object in an image. The model consists of a Vision Transformer (ViT) with a lightweight head on top.
+
+<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/vitmatte_architecture.png"
+alt="drawing" width="600"/>
+
+<small> ViTMatte high-level overview. Taken from the <a href="https://arxiv.org/abs/2305.15272">original paper.</a> </small>
+
+## Intended uses & limitations
+
+You can use the raw model for image matting. See the [model hub](https://huggingface.co/models?search=vitmatte) to look for other
+fine-tuned versions that may interest you.
+
+### How to use
+
+We refer to the [docs](https://huggingface.co/docs/transformers/main/en/model_doc/vitmatte#transformers.VitMatteForImageMatting.forward.example).
+
+### BibTeX entry and citation info
+
+```bibtex
+@misc{yao2023vitmatte,
+      title={ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers}, 
+      author={Jingfeng Yao and Xinggang Wang and Shusheng Yang and Baoyuan Wang},
+      year={2023},
+      eprint={2305.15272},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV}
+}
+```

ComfyUI/models/vitmatte/config.json

@@ -0,0 +1,53 @@
+{
+  "_commit_hash": null,
+  "architectures": [
+    "VitMatteForImageMatting"
+  ],
+  "backbone_config": {
+    "hidden_size": 384,
+    "image_size": 512,
+    "model_type": "vitdet",
+    "num_attention_heads": 6,
+    "num_channels": 4,
+    "out_features": [
+      "stage12"
+    ],
+    "out_indices": [
+      12
+    ],
+    "residual_block_indices": [
+      2,
+      5,
+      8,
+      11
+    ],
+    "use_relative_position_embeddings": true,
+    "window_block_indices": [
+      0,
+      1,
+      3,
+      4,
+      6,
+      7,
+      9,
+      10
+    ],
+    "window_size": 14
+  },
+  "convstream_hidden_sizes": [
+    48,
+    96,
+    192
+  ],
+  "fusion_hidden_sizes": [
+    256,
+    128,
+    64,
+    32
+  ],
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "model_type": "vitmatte",
+  "torch_dtype": "float32",
+  "transformers_version": null
+}

ComfyUI/models/vitmatte/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bda9289db1bb6762d978b42d1c62ae3f34daf7497171a347a1d09657efd788cb
+size 103294572

ComfyUI/models/vitmatte/preprocessor_config.json

@@ -0,0 +1,18 @@
+{
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "VitMatteImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "rescale_factor": 0.00392156862745098,
+  "size_divisibility": 32
+}

ComfyUI/models/vitmatte/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ec6aed44bc8d8ab7f4d0ff46da3520a534cf5a97a8262404ff6efa9ae33b1e5
+size 103349013