├── .gitignore ├── README.md ├── __init__.py └── configs └── clip_vision_siglip2_so400m_512.json /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Distribution / packaging 10 | .Python 11 | build/ 12 | develop-eggs/ 13 | dist/ 14 | downloads/ 15 | eggs/ 16 | .eggs/ 17 | lib/ 18 | lib64/ 19 | parts/ 20 | sdist/ 21 | var/ 22 | wheels/ 23 | share/python-wheels/ 24 | *.egg-info/ 25 | .installed.cfg 26 | *.egg 27 | MANIFEST 28 | 29 | # PyInstaller 30 | # Usually these files are written by a python script from a template 31 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 32 | *.manifest 33 | *.spec 34 | 35 | # Installer logs 36 | pip-log.txt 37 | pip-delete-this-directory.txt 38 | 39 | # Unit test / coverage reports 40 | htmlcov/ 41 | .tox/ 42 | .nox/ 43 | .coverage 44 | .coverage.* 45 | .cache 46 | nosetests.xml 47 | coverage.xml 48 | *.cover 49 | *.py,cover 50 | .hypothesis/ 51 | .pytest_cache/ 52 | cover/ 53 | 54 | # Translations 55 | *.mo 56 | *.pot 57 | 58 | # Django stuff: 59 | *.log 60 | local_settings.py 61 | db.sqlite3 62 | db.sqlite3-journal 63 | 64 | # Flask stuff: 65 | instance/ 66 | .webassets-cache 67 | 68 | # Scrapy stuff: 69 | .scrapy 70 | 71 | # Sphinx documentation 72 | docs/_build/ 73 | 74 | # PyBuilder 75 | .pybuilder/ 76 | target/ 77 | 78 | # Jupyter Notebook 79 | .ipynb_checkpoints 80 | 81 | # IPython 82 | profile_default/ 83 | ipython_config.py 84 | 85 | # pyenv 86 | # For a library or package, you might want to ignore these files since the code is 87 | # intended to run in multiple environments; otherwise, check them in: 88 | # .python-version 89 | 90 | # pipenv 91 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 92 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 93 | # having no cross-platform support, pipenv may install dependencies that don't work, or not 94 | # install all needed dependencies. 95 | #Pipfile.lock 96 | 97 | # poetry 98 | # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control. 99 | # This is especially recommended for binary packages to ensure reproducibility, and is more 100 | # commonly ignored for libraries. 101 | # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control 102 | #poetry.lock 103 | 104 | # pdm 105 | # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control. 106 | #pdm.lock 107 | # pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it 108 | # in version control. 109 | # https://pdm.fming.dev/#use-with-ide 110 | .pdm.toml 111 | 112 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm 113 | __pypackages__/ 114 | 115 | # Celery stuff 116 | celerybeat-schedule 117 | celerybeat.pid 118 | 119 | # SageMath parsed files 120 | *.sage.py 121 | 122 | # Environments 123 | .env 124 | .venv 125 | env/ 126 | venv/ 127 | ENV/ 128 | env.bak/ 129 | venv.bak/ 130 | 131 | # Spyder project settings 132 | .spyderproject 133 | .spyproject 134 | 135 | # Rope project settings 136 | .ropeproject 137 | 138 | # mkdocs documentation 139 | /site 140 | 141 | # mypy 142 | .mypy_cache/ 143 | .dmypy.json 144 | dmypy.json 145 | 146 | # Pyre type checker 147 | .pyre/ 148 | 149 | # pytype static type analyzer 150 | .pytype/ 151 | 152 | # Cython debug symbols 153 | cython_debug/ 154 | 155 | # PyCharm 156 | # JetBrains specific template is maintained in a separate JetBrains.gitignore that can 157 | # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore 158 | # and can be added to the global gitignore or merged into this file. For a more nuclear 159 | # option (not recommended) you can uncomment the following to ignore the entire idea folder. 160 | .idea/ 161 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # ComfyUI Advanced Vision 2 | 3 | This is a custom node for the [ComfyUI](https://github.com/comfyanonymous/ComfyUI) project to support loading more vision models. 4 | It will fallback to the default loading if comfy supported models are detected. Meaning this node can be used as a drop-in replacement for the "Load Clip Vision" node. 5 | 6 | The supported vision models can be found here at huggingface [ostris/ComfyUI-Advanced-Vision](https://huggingface.co/ostris/ComfyUI-Advanced-Vision). Put them in the `models/clip_vision` directory. 7 | 8 | ### Supported Models 9 | 10 | - [google/siglip2-so400m-patch16-512](https://huggingface.co/google/siglip2-so400m-patch16-512) 11 | 12 | ### Installation 13 | 14 | Clone this repo into the `custom_nodes` directory of the ComfyUI project. 15 | -------------------------------------------------------------------------------- /__init__.py: -------------------------------------------------------------------------------- 1 | import os 2 | import logging 3 | import comfy.clip_vision 4 | from comfy.utils import load_torch_file 5 | import folder_paths 6 | 7 | 8 | def load_advanced_vision_from_sd(sd, prefix="", convert_keys=False): 9 | config_root = os.path.join(os.path.dirname( 10 | os.path.realpath(__file__)), "configs") 11 | json_config = None 12 | if convert_keys: 13 | sd = comfy.clip_vision.convert_to_transformers(sd, prefix) 14 | if "vision_model.encoder.layers.22.layer_norm1.weight" in sd: 15 | if sd["vision_model.encoder.layers.0.layer_norm1.weight"].shape[0] == 1152: 16 | if sd["vision_model.embeddings.position_embedding.weight"].shape[0] == 1024: 17 | json_config = os.path.join( 18 | config_root, 19 | "clip_vision_siglip2_so400m_512.json" 20 | ) 21 | print("Advanced Vision Model: clip_vision_siglip2_so400m_512 detected") 22 | 23 | if json_config is None: 24 | return None 25 | 26 | clip = comfy.clip_vision.ClipVisionModel(json_config) 27 | m, u = clip.load_sd(sd) 28 | if len(m) > 0: 29 | logging.warning("missing clip vision: {}".format(m)) 30 | u = set(u) 31 | keys = list(sd.keys()) 32 | for k in keys: 33 | if k not in u: 34 | sd.pop(k) 35 | return clip 36 | 37 | 38 | def load_advanced_vision(ckpt_path): 39 | sd = load_torch_file(ckpt_path) 40 | if "visual.transformer.resblocks.0.attn.in_proj_weight" in sd: 41 | return load_advanced_vision_from_sd(sd, prefix="visual.", convert_keys=True) 42 | else: 43 | return load_advanced_vision_from_sd(sd) 44 | 45 | 46 | class AdvancedVisionLoader: 47 | @classmethod 48 | def INPUT_TYPES(s): 49 | return { 50 | "required": { 51 | "clip_name": (folder_paths.get_filename_list("clip_vision"), ), 52 | }} 53 | RETURN_TYPES = ("CLIP_VISION",) 54 | FUNCTION = "load_vision" 55 | 56 | CATEGORY = "loaders" 57 | 58 | def load_vision(self, clip_name): 59 | clip_path = folder_paths.get_full_path_or_raise( 60 | "clip_vision", 61 | clip_name 62 | ) 63 | # try to load it through ours first 64 | clip_vision = load_advanced_vision(clip_path) 65 | 66 | # load it through comfy 67 | if clip_vision is None: 68 | clip_vision = comfy.clip_vision.load(clip_path) 69 | return (clip_vision,) 70 | 71 | 72 | NODE_CLASS_MAPPINGS = { 73 | "AdvancedVisionLoader": AdvancedVisionLoader, 74 | } 75 | 76 | NODE_DISPLAY_NAME_MAPPINGS = { 77 | "AdvancedVisionLoader": "Load Advanced Vision Model", 78 | } 79 | -------------------------------------------------------------------------------- /configs/clip_vision_siglip2_so400m_512.json: -------------------------------------------------------------------------------- 1 | { 2 | "num_channels": 3, 3 | "hidden_act": "gelu_pytorch_tanh", 4 | "hidden_size": 1152, 5 | "image_size": 512, 6 | "intermediate_size": 4304, 7 | "model_type": "siglip_vision_model", 8 | "num_attention_heads": 16, 9 | "num_hidden_layers": 27, 10 | "patch_size": 16, 11 | "image_mean": [0.5, 0.5, 0.5], 12 | "image_std": [0.5, 0.5, 0.5] 13 | } 14 | --------------------------------------------------------------------------------