EVA CLIP is EVA02-CLIP-L-14-336, error

[chaorenai]

The EVA CLIP is EVA02-CLIP-L-14-336, but should be downloaded automatically (will be located in the huggingface directory).

I don't know why it can't be downloaded automatically. There is no manual download address either...

---

File "D:\ComfyUI\custom_nodes\PuLID_ComfyUI\eva_clip\pretrained.py", line 300, in download_pretrained_from_hf cached_file = hf_hub_download(model_id, filename, revision=revision, cache_dir=cache_dir) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\sunny.conda\envs\comfyui\Lib\site-packages\huggingface_hub\utils_validators.py", line 118, in _inner_fn return fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^ File "C:\Users\sunny.conda\envs\comfyui\Lib\site-packages\huggingface_hub\file_download.py", line 1406, in hf_hub_download raise LocalEntryNotFoundError( huggingface_hub.utils._errors.LocalEntryNotFoundError: An error happened while trying to locate the file on the Hub and we cannot find the requested files in the local cache. Please check your connection and try again or make sure your Internet connection is on.

[jingruixiaoxiao]

I have the same problem, EVA02-CLIP-L-14-336 does not automatically download from huggingface. Tip: “An error happened while trying to locate the file on the Hub and we cannot find the requested files in the local cache. Please check your connection and try again or make sure your Internet connection is on.” But I made sure the network is fine. But it won't download and I know where the downloaded path is!

[kelvinyoung]

same error

[cubiq]

https://github.com/cubiq/PuLID_ComfyUI/issues/8

[winjvlee]

I placed the file I downloaded, EVA02_CLIP_L_336_psz14_s6B.pt, in the folder on my local machine at ~/.cache/huggingface/hub/models--QuanSun--EVA-CLIP/snapshots/11afd202f2ae80869d6cef18b1ec775e79bd8d12/. However, after running it, I still get the same error message................... It seems that downloading one file is not enough, there are many files to download, if the environment is not smooth, still can not use

[mylonesky-bot]

metoo...

[8306603]

me too

[LL020202]

I placed the file I downloaded, EVA02_CLIP_L_336_psz14_s6B.pt, in the folder on my local machine at ~/.cache/huggingface/hub/models--QuanSun--EVA-CLIP/snapshots/11afd202f2ae80869d6cef18b1ec775e79bd8d12/. However, after running it, I still get the same error message................... It seems that downloading one file is not enough, there are many files to download, if the environment is not smooth, still can not use

This method is actually possible, but it still requires a file, models -- QuanSun -- EVA CLIP/refs/main, with the file content being 11afd202f2ae80869d6cef18b1ec775e79bd8d12 for testing and can be used

[8306603]

I placed the file I downloaded, EVA02_CLIP_L_336_psz14_s6B.pt, in the folder on my local machine at ~/.cache/huggingface/hub/models--QuanSun--EVA-CLIP/snapshots/11afd202f2ae80869d6cef18b1ec775e79bd8d12/. However, after running it, I still get the same error message................... It seems that downloading one file is not enough, there are many files to download, if the environment is not smooth, still can not use

This method is actually possible, but it still requires a file, models -- QuanSun -- EVA CLIP/refs/main, with the file content being 11afd202f2ae80869d6cef18b1ec775e79bd8d12 for testing and can be used

thanks,It's working.

[ranchen3010]

I saw a lot of EVA files in -QuanSun--EVA-CLIP. When I only downloaded EVA02_CLIP_L_336_psz14_s6B.pt and models -- QuanSun -- EVA CLIP/refs/main, I still got an error. Should I put all the files on huggingface? Can it be used after downloading everything?

[jesenzhang]

Why not just put the chekpoint in the path /models/eva_clips and Load_EVA_Clip with checkpoint name list like ipadapter loader? And models/facedection is already used by reactor, so I add the path FACEDETECTION_DIR = os.path.join(folder_paths.models_dir, "facedetection") if "facedetection" not in folder_paths.folder_names_and_paths: current_paths = [FACEDETECTION_DIR] else: current_paths, _ = folder_paths.folder_names_and_paths["facedetection"] folder_paths.folder_names_and_paths["facedetection"] = (current_paths, folder_paths.supported_pt_extensions) and add the model_rootpath to FaceRestoreHelper face_helper = FaceRestoreHelper( upscale_factor=1, face_size=512, crop_ratio=(1, 1), det_model='retinaface_resnet50', save_ext='png', device=device, model_rootpath=FACEDETECTION_DIR )

[taiyouZhang]

My cache path is .cache/huggingface/hub/models--QuanSun--EVA-CLIP, just put download file in this folder

with pdb, the download codes is in ComfyUI/custom_nodes/PuLID_ComfyUI/eva_clip/pretrained.py

def download_pretrained_from_hf( model_id: str, filename: str = 'open_clip_pytorch_model.bin', revision=None, cache_dir: Union[str, None] = None, ): has_hf_hub(True) cached_file = hf_hub_download(model_id, filename, revision=revision, cache_dir=cache_dir) return cached_file

[modyfaer]

Loaded EVA02-CLIP-L-14-336 model config. Shape of rope freq: torch.Size([576, 64]) Loading pretrained EVA02-CLIP-L-14-336 weights (eva_clip). incompatible_keys.missing_keys: ['visual.rope.freqs_cos', 'visual.rope.freqs_sin', 'visual.blocks.0.attn.rope.freqs_cos', 'visual.blocks.0.attn.rope.freqs_sin', 'visual.blocks.1.attn.rope.freqs_cos', 'visual.blocks.1.attn.rope.freqs_sin', 'visual.blocks.2.attn.rope.freqs_cos', 'visual.blocks.2.attn.rope.freqs_sin', 'visual.blocks.3.attn.rope.freqs_cos', 'visual.blocks.3.attn.rope.freqs_sin', 'visual.blocks.4.attn.rope.freqs_cos', 'visual.blocks.4.attn.rope.freqs_sin', 'visual.blocks.5.attn.rope.freqs_cos', 'visual.blocks.5.attn.rope.freqs_sin', 'visual.blocks.6.attn.rope.freqs_cos', 'visual.blocks.6.attn.rope.freqs_sin', 'visual.blocks.7.attn.rope.freqs_cos', 'visual.blocks.7.attn.rope.freqs_sin', 'visual.blocks.8.attn.rope.freqs_cos', 'visual.blocks.8.attn.rope.freqs_sin', 'visual.blocks.9.attn.rope.freqs_cos', 'visual.blocks.9.attn.rope.freqs_sin', 'visual.blocks.10.attn.rope.freqs_cos', 'visual.blocks.10.attn.rope.freqs_sin', 'visual.blocks.11.attn.rope.freqs_cos', 'visual.blocks.11.attn.rope.freqs_sin', 'visual.blocks.12.attn.rope.freqs_cos', 'visual.blocks.12.attn.rope.freqs_sin', 'visual.blocks.13.attn.rope.freqs_cos', 'visual.blocks.13.attn.rope.freqs_sin', 'visual.blocks.14.attn.rope.freqs_cos', 'visual.blocks.14.attn.rope.freqs_sin', 'visual.blocks.15.attn.rope.freqs_cos', 'visual.blocks.15.attn.rope.freqs_sin', 'visual.blocks.16.attn.rope.freqs_cos', 'visual.blocks.16.attn.rope.freqs_sin', 'visual.blocks.17.attn.rope.freqs_cos', 'visual.blocks.17.attn.rope.freqs_sin', 'visual.blocks.18.attn.rope.freqs_cos', 'visual.blocks.18.attn.rope.freqs_sin', 'visual.blocks.19.attn.rope.freqs_cos', 'visual.blocks.19.attn.rope.freqs_sin', 'visual.blocks.20.attn.rope.freqs_cos', 'visual.blocks.20.attn.rope.freqs_sin', 'visual.blocks.21.attn.rope.freqs_cos', 'visual.blocks.21.attn.rope.freqs_sin', 'visual.blocks.22.attn.rope.freqs_cos', 'visual.blocks.22.attn.rope.freqs_sin', 'visual.blocks.23.attn.rope.freqs_cos', 'visual.blocks.23.attn.rope.freqs_sin']

[cubiq]

that's fine

[thinker-sheldon]

I placed the file I downloaded, EVA02_CLIP_L_336_psz14_s6B.pt, in the folder on my local machine at ~/.cache/huggingface/hub/models--QuanSun--EVA-CLIP/snapshots/11afd202f2ae80869d6cef18b1ec775e79bd8d12/. However, after running it, I still get the same error message................... It seems that downloading one file is not enough, there are many files to download, if the environment is not smooth, still can not use

This method is actually possible, but it still requires a file, models -- QuanSun -- EVA CLIP/refs/main, with the file content being 11afd202f2ae80869d6cef18b1ec775e79bd8d12 for testing and can be used

thanks,It's working.

I tried this, but it didn't work. The model keeps reporting errors.

[cchihirooRR]

Hello Matteo,

Thank you for your outstanding work—the nodes and tutorials have been incredibly helpful to me. I came across the PuLID video on YouTube, which was truly impressive. However, in the process of using this node, I encountered issues similar to those with EVA02-CLIP-L-14-336, and it seems there is currently no reliable solution (if there is already a solution, could you please let me know directly, as my English might not be good enough to miss it). Please fix it if possible—should PuLID be applicable to commercial processes, I can apply for sponsorship from my institution to help you focus more on development work. Thank you once again for everything you've done.