Are you ready for an extraordinary journey into the world of AI and graphics software?
If you are new in AI and graphics software or you want to improve your skills as a professional, you are at the right place.
"CgTopTips" shares a wide range of tutorials from the beginner level to the upper levels on our up-to-date KZread channel.
Our team provides a great number of videos which are too detailed and providing fundamental information.
New videos are coming every day, don’t miss to check our channel :)
openart.ai/workflows/@cgtips
facebook.com/cgtoptips
twitter.com/cgtoptips
[email protected]
#CgTopTips
Пікірлер
Didn't work for me, getting tons of error.
Merhaba, her şeyi yaptım ama bu hatayı alıyorum :( Even though I upload BiRefNet files, it still gives an error :/ Error occurred when executing BiRefNet: Model loading failed: [Errno 2] No such file or directory: 'C:\\Users\\xxx\\Desktop\ ew_ComfyUI_windows_portable_nvidia_cu121_or_cpu\\ComfyUI_windows_portable\\ComfyUI\\models\\BiRefNet\\swin_large_patch4_window12_384_22kto1k.pth' File "C:\Users\xxx\Desktop ew_ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\xxx\Desktop ew_ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\execution.py", line 81, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\xxx\Desktop ew_ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\xxx\Desktop ew_ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-BiRefNet\BiRefNet_node.py", line 101, in matting self.load(weight_path, device=device) File "C:\Users\xxx\Desktop ew_ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-BiRefNet\BiRefNet_node.py", line 67, in load raise RuntimeError(f"Model loading failed: {e}")
Is there a specific reason why you don't include the links in the video in the description? I'm not lazy, this was just a question for me 😁😁❤❤
Do we need to download the BiRefNet models separately? Apparently it doesn't do so automatically... Thank you by the way!
Even though I upload BiRefNet files, it still gives an error :/
@@valorantacemiyimben You need to place the models under the BiRefNet folder inside your ComfyUI models folder The path should look like this: "ComfyUI\models\BiRefNet" In that folder you need to download 6 models, total size is 3.06GB Here are the model names you should have there: - BiRefNet-DIS_ep580.pth - BiRefNet-ep480.pth - pvt_v2_b2.pth - pvt_v2_b5.pth - swin_base_patch4_window12_384_22kto1k.pth - swin_large_patch4_window12_384_22kto1k.pth
tnx for video CG TOP...... Please teach how to make A to B morph ......Is it possible to train this workflow? I leave the link below Because it is very dumb and very disorganized And it's different from your helpful tutorial videos Thank you kzread.info/dash/bejne/paOo19OegNvFnto.html
Hello, the workflow is not on your site. how can we download
çok zor. pencerelere alışamadım.
Bu iş akışı diğer iş akışlarına kıyasla daha basittir. Bol pratikle sizin için normal hale gelecektir
Anyone know if this can work on mac M3, I am recieving this error code currently if anyone knows how to help. "Error occurred when executing LivePortraitVideoNode: Torch not compiled with CUDA enabled File "/Users/leepreston/Desktop/AI/ComfyUI/execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/leepreston/Desktop/AI/ComfyUI/execution.py", line 81, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/leepreston/Desktop/AI/ComfyUI/execution.py", line 65, in map_node_over_list results.append(getattr(obj, func)(**input_data_all)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/leepreston/Desktop/AI/ComfyUI/custom_nodes/comfyui-liveportrait/nodes/live_portrait.py", line 468, in run live_portrait_pipeline = LivePortraitPipeline( ^^^^^^^^^^^^^^^^^^^^^ File "/Users/leepreston/Desktop/AI/ComfyUI/custom_nodes/comfyui-liveportrait/nodes/LivePortrait/src/live_portrait_pipeline.py", line 67, in __init__ self.live_portrait_wrapper: LivePortraitWrapper = LivePortraitWrapper(cfg=inference_cfg) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/leepreston/Desktop/AI/ComfyUI/custom_nodes/comfyui-liveportrait/nodes/LivePortrait/src/live_portrait_wrapper.py", line 29, in __init__ self.appearance_feature_extractor = load_model(cfg.checkpoint_F, model_config, cfg.device_id, 'appearance_feature_extractor') ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/leepreston/Desktop/AI/ComfyUI/custom_nodes/comfyui-liveportrait/nodes/LivePortrait/src/utils/helper.py", line 99, in load_model model = AppearanceFeatureExtractor(**model_params).cuda(device) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/opt/homebrew/lib/python3.11/site-packages/torch/nn/modules/module.py", line 915, in cuda return self._apply(lambda t: t.cuda(device)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/opt/homebrew/lib/python3.11/site-packages/torch/nn/modules/module.py", line 779, in _apply module._apply(fn) File "/opt/homebrew/lib/python3.11/site-packages/torch/nn/modules/module.py", line 779, in _apply module._apply(fn) File "/opt/homebrew/lib/python3.11/site-packages/torch/nn/modules/module.py", line 804, in _apply param_applied = fn(param) ^^^^^^^^^ File "/opt/homebrew/lib/python3.11/site-packages/torch/nn/modules/module.py", line 915, in return self._apply(lambda t: t.cuda(device)) ^^^^^^^^^^^^^^ File "/opt/homebrew/lib/python3.11/site-packages/torch/cuda/__init__.py", line 284, in _lazy_init raise AssertionError("Torch not compiled with CUDA enabled")
Cool, how chang pose my foto, not prompt?
Any reason why i am not seeing option in search for MimicMotion Sampler and MimicMotion Getposes ?
Try update the Mimic Motion and then completely close and reopen the program, maybe it help !
@@CgTopTips and we have to install the mimicmotion custom node from comfyUI itself right? I am not sure why my comfyui is looking at /notebooks/ComfyUI/custom_nodes/MimicMotion/__init__.p . Where as at git repo __init__p is inside MimicMotion/mimicmotion
gracias por compartir , ayudaria si tiene subtitulos saludos
Hello and thanks, I'm using Mimic but a problem I have is the background, moving along the dancer... How I can fix it? Thank you!
tell me what the problem is, it takes a very long time to render for more than an hour and then such a result and there are no errors. the video that turned out to have a black square instead of a head.
Prolonged render time could be due to one of the following options: 1. You are using the CPU instead of the GPU. 2. The program is downloading its required files for the first time (though the render should not be lengthy on the second run). 3. Your settings, such as video duration, size, or the number of steps, are high!
👍👍👍🙏
Thank you for the help, My images are looking better now. Hive Five
How many computer specs are required to use this program?
Minimum 8GB VRAM !
Set notebook specs?
Sir i getting this error. Error occurred when executing DownloadAndLoadMimicMotionModel: Error no file named config.json found in directory C:\Users\akash\Documents\ComfyUI_windows_portable\ComfyUI\models\diffusers\stable-video-diffusion-img2vid-xt-1-
Make sure you have downloaded all `config.json` files according to the video, or that their names exactly match those shown in the video
@@CgTopTips I downloaded and check many time I placed all model and jason file correctly
Error occurred when executing DownloadAndLoadMimicMotionModel: Error no file named config.json found in directory
Make sure you have downloaded the `config.json` files according to the video, or that their names exactly match those shown in the video.
how to render all frames. it only gives few frames animated and that goes in loop.what setting need to be changed to render all dance moves. kzread.info/dash/bejne/YqSX29ZxiMy5ldY.html
Did you set the frame_load_cap to zero?
@@CgTopTips no i think i just left it as it is given in the workflow. i think frame_load_cap was either the one in example workflow which was 15 or your workflow which was 24.should it be set to zero to render all frames? one more question is with 8 gb vram will i be able to render mimic motion video of 20 minutes long. thanks
Unfortunately No ! "For a 640x360 (nHD) video, you can only get approximately 40 frames as output."
@@CgTopTips kzread.info/dash/bejne/aYWNycOwmMzWe7A.html hi i managed to create a motion video but facial features not perfect. thanks so much for assistance. you are great help in learning
Increase the resolusion or use face detailer or face swap
Thanks! I'm grabbin' 'em all.
작동하지 않아요 애러가 너무 많습니다.
비디오를 따라 진행하고 있는지 확인하시고, 오류 메시지를 받으시면 공유해 주세요. 제가 도와드릴 수 있을지도 모릅니다
@@CgTopTips 도움을 요청드립니다. 동일한 노드와 값으로 진행했습니다만. 하기와 같이 'MimicMotion Sampler'단계에서 에러가 발생합니다. --------▼▼▼▼▼▼▼-------- Error occurred when executing MimicMotionSampler: "compute_index_ranges_weights" not implemented for 'Half' File "/Volumes/R_SSD/ML/ComfyUI/execution.py", line 152, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Volumes/R_SSD/ML/ComfyUI/execution.py", line 82, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Volumes/R_SSD/ML/ComfyUI/execution.py", line 75, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Volumes/R_SSD/ML/ComfyUI/custom_nodes/ComfyUI-MimicMotionWrapper/nodes.py", line 294, in process frames = pipeline( ^^^^^^^^^ File "/opt/miniconda3/envs/comfy/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "/Volumes/R_SSD/ML/ComfyUI/custom_nodes/ComfyUI-MimicMotionWrapper/mimicmotion/pipelines/pipeline_mimicmotion.py", line 521, in __call__ image_embeddings = self._encode_image(image, device, num_videos_per_prompt, self.do_classifier_free_guidance, image_embed_strength=image_embed_strength) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Volumes/R_SSD/ML/ComfyUI/custom_nodes/ComfyUI-MimicMotionWrapper/mimicmotion/pipelines/pipeline_mimicmotion.py", line 152, in _encode_image image = clip_preprocess(image.clone(), 224) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Volumes/R_SSD/ML/ComfyUI/comfy/clip_vision.py", line 25, in clip_preprocess image = torch.nn.functional.interpolate(image, size=(round(scale * image.shape[2]), round(scale * image.shape[3])), mode="bicubic", antialias=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/opt/miniconda3/envs/comfy/lib/python3.11/site-packages/torch/nn/functional.py", line 4589, in interpolate return torch._C._nn._upsample_bicubic2d_aa( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Awesome results but...why my video creation is on slow motion? did i do something wrong?
Change frame_rate in video combine node to 25 fps
@@CgTopTips thank you bruh!!
tnx for video.....I sent you an email, but I have been waiting for a reply for a long time I sent another email today
Whats your pc specs btw
RTX 4060, 8GB VRAM
this is livetime?
No, but it has good processing speed. Make sure your input video's size is not too large
Do you know of a way to crop/resize the video to a square shape that will work in 'this' workflow without distorting the original image? Usually, I'd use image resize or prepare images for clip vision, but they don't work here because of the connectors.
Use ImageCrop node
@CgTopTips thanks for a suggestion. Could you send a picture please? I tried to connect "load video and segment" to two different image crop nodes, but they don't connect. I could crop a video if I use a different load video node, but then I can't connect into the 'drive video' connector in the live portrait node. Thank you
Thanks!! I have an issue btw. The "insightface" folder didn't appear in my "models" folder. I am sure I downloaded the nods you mentioned at the beginning of the video. Maybe I'm doing something wrong. What do you think?
Manually create that folder and put the model
Followed instructions. I'm not an expert at all. Just a "watch & Mimic" guy. It retrieves me a error on LivePortrait Video Node (#7) Does it only work with default LivePortrait Driving Video? Error occurred when executing LivePortraitVideoNode: [Errno 2] No such file or directory: '/ComfyUI/models/liveportrait/base_models/appearance_feature_extractor.pth' File "/ComfyUI/execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "/ComfyUI/execution.py", line 81, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) File "/ComfyUI/execution.py", line 65, in map_node_over_list results.append(getattr(obj, func)(**input_data_all)) File "/ComfyUI/custom_nodes/comfyui-liveportrait/nodes/live_portrait.py", line 468, in run live_portrait_pipeline = LivePortraitPipeline( File "/ComfyUI/custom_nodes/comfyui-liveportrait/nodes/LivePortrait/src/live_portrait_pipeline.py", line 67, in __init__ self.live_portrait_wrapper: LivePortraitWrapper = LivePortraitWrapper(cfg=inference_cfg) File "/ComfyUI/custom_nodes/comfyui-liveportrait/nodes/LivePortrait/src/live_portrait_wrapper.py", line 29, in __init__ self.appearance_feature_extractor = load_model(cfg.checkpoint_F, model_config, cfg.device_id, 'appearance_feature_extractor') File "/ComfyUI/custom_nodes/comfyui-liveportrait/nodes/LivePortrait/src/utils/helper.py", line 134, in load_model model.load_state_dict(torch.load(ckpt_path, map_location=lambda storage, loc: storage)) File "/venv/lib/python3.10/site-packages/torch/serialization.py", line 997, in load with _open_file_like(f, 'rb') as opened_file: File "/venv/lib/python3.10/site-packages/torch/serialization.py", line 444, in _open_file_like return _open_file(name_or_buffer, mode) File "/venv/lib/python3.10/site-packages/torch/serialization.py", line 425, in __init__ super().__init__(open(name, mode))
Hi .is it still 24vram till now?
Unfortunately, this is more of a promotional aspect, and the VRAM is below 8GB at most! Overall, this platform is better suited for beginners for learning purposes
@@CgTopTips thanks man. If you know any way to be able to render with Vram higher than 8.. please tell me. I need high vram and it should be free
Due to this : 'When installing or updating this custom node, many installation packages may be downgraded due to the installation of requirements. !! python3.12 is incompatible.' > are there any other SAM nodes you would recommend, or ...or - did you encounter any colisions mentioned, or... or... just don't worry ... > ? Heh, I am little scared to install that node, i don't want my fragile Comfie to burn to the floor... ...so...I made the step... :D and everything seems ok... but when I used their (ZHO) basic workflow, everything run ok-ish with the yolo_world/l, but crashes with /m ans /s > 'cannot reshape tensor of 0 elements into shape [-1, 1, 1, 0] because the unspecified dimension size -1 can be any value and is ambiguous' ... i suppose that 'l' is for large, 'm' is for medium and 's' is for small ... so when it run with 'l', I should be good, isn't it so? Also, how is it with that 'inpaint' versions of models? I thought the 'inpaint' is somehow obsolete and nortmal models can be used for inpaint too, or am I delusional? And for the last > I did take a look at the 'Brushnet' video you mentioned in previous video comments, but there is no outpainting also. Is there a way to OUTpaint in ComfyUI? Thanks for all you do for us ;-) p.s.: I can imagine > enlarge the image I want to outpaint in something like mspaint, and than that enlarged blank area inpaint in comfy....is that the right way to 'outpaint' ?
Had the same issue. Downgraded python to 3.10 and still got the same error.
Could you please add a node to load a reference face pic? Thank you
Thanks, the workflow works, and it did a pretty good job upscaling a 512x512 image to a 2048x2048 one. I have a Nvidia GTX 1060 6gb card, the whole process took around 20 minutes to finish. I then downloaded the v2_rank256 version of controlnet model and tried upscaling using that in hopes I could make the process way faster by sacrificing some quality, but it took around the same time unfortunately. I used the same exact workflow, the only thing I have different in my workflow is my checkpoint (Juggernaut instead of dreamshaper). ~20 mins does not seem that low vram friendly
My graphics card is an RTX 4060 8Gb VRAM, and with the settings in the video, it generates a 1024x1024 image in two minutes. Other upscaling methods, like using Supir, result in an "Out of memory" error !
@@CgTopTips How long does the upscaling process take you tho?
@@mikrodizels 2~3 min (RTX 4090 8gb vram -1024x1024)
@@CgTopTips You mean to just generate a 1024x1024 image? Or to upscale a 1024x1024 image, using this workflow and these settings?
The photo I uploaded was 150×150 pixels, and I upscaled it to 1024×1024 pixels using the this workflow
This looks very cool but I'm afraid of ZHO_ZHO_ZHO packages now, I always had issues with them in the past xD
Error occurred when executing Yoloworld_ESAM_Zho: cannot import name 'packaging' from 'pkg_resources' (J:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\pkg_resources\__init__.py)
Always make sure to follow the installation steps for each custom node precisely through its GitHub page, and ensure that the custom node is correctly installed on your computer. - Make sure to install the requirement files for each custom node and download the necessary models. The best way to troubleshoot is to read the ComfyUI Terminal Panel.
Wonderful video. Thank you!
🙏
Thanks for the video! It just goes forever, I waited for 30 minutes for a single picture of 163kb to upscale and it was still not done, so I cancelled the process.
Check the terminal panel to ensure that no model is currently downloading. Are you using a graphics card or CPU? Did you set up the nodes exactly like in the video? ...
error not install "LivePortraitVideoNode"
Always check the following points: - Ensure you install the requirement files for each custom node (pip install -r requirements.txt). - Download the necessary models for each custom node. - Verify that all custom nodes needed for the workflow are installed without issues (check through the manager panel). - Ensure there are no version conflicts between models; for example, if the checkpoint is SD1.5, the ControlNet should also be SD1.5. - Always follow the installation steps for each custom node precisely through its GitHub page. - The best way to understand an issue when you see an error message is the ComfyUI Terminal Panel. For example, sizes might not match, or you might not have selected the settings for a node correctly, and so on. - You can copy the error message and search for a solution on Google. Note: If the problem is still unresolved, please share a screen shot of error with your workflow via email so I can check it.
thank you for your work, would you mind to showcase inpaint and outpaint. Are there necessary inpaint/outpaint(?) models still? How to properly outpaint in comfy?
Did you watch BrushNet video ?
@@CgTopTips I will !
Works for me! I was getting seams but they went away after I changed the seam_fix_mode to "Half Tile" on the second upscaler. Thanks for the workflow -- I learned a lot.
How do you add pretext, appended text?
I noticed something: When I tried with another dancer, her face was covered by her hand for a few frames. I immediately got an error message (like) "Face not recognized". The process aborted and the entire result was discarded. That means the entire rendering time was wasted. Do you have any idea how to make the tool continue rendering despite the error message? Perhaps an additional box in the ComfyUI that catches the error?
Unfortunately, in this method, the face must be visible in all frames, and there is currently no solution for this issue !
@@CgTopTips THX!
Hi. I had a look at the temporary files. I noticed something: With your method, it seems that for EVERY frame of the source video, a complete pass with the facial expressions of the target video is made. This means that at 30 fps and 1 second (for the result), for example, 30x30 = 900 images are generated per second (at 30 fps of the source video). However, only 30 images are needed for the result, the other 870 images are discarded. I understand that comparison images are needed for consistent movement. But wouldn't 5 comparison images be enough, for example, instead of the full second? If I render 10 seconds of video, for example (at 30 fps), the result for 300 video images is 10*30*30=9000 generated images. That's crazy and needs a lot of time. Do you have a solution for this.
thank you , that was helpful
i got error bro this is my error how to i fix it Error occurred when executing DownloadAndLoadMimicMotionModel: Error no file named config.json found in directory E:\ComfyUI\ComfyUI_windows_portable\ComfyUI\models\diffusers\stable-video-diffusion-img2vid-xt-1-1. File "E:\ComfyUI\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\ComfyUI\ComfyUI_windows_portable\ComfyUI\execution.py", line 81, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\ComfyUI\ComfyUI_windows_portable\ComfyUI\execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\ComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-MimicMotionWrapper odes.py", line 128, in loadmodel self.vae = AutoencoderKLTemporalDecoder.from_pretrained(svd_path, subfolder="vae", variant="fp16", low_cpu_mem_usage=True).to(dtype).to(device).eval() ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\ComfyUI\ComfyUI_windows_portable\python_embeded\Lib\site-packages\huggingface_hub\utils\_validators.py", line 114, in _inner_fn return fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^ File "E:\ComfyUI\ComfyUI_windows_portable\python_embeded\Lib\site-packages\diffusers\models\modeling_utils.py", line 616, in from_pretrained config, unused_kwargs, commit_hash = cls.load_config( ^^^^^^^^^^^^^^^^ File "E:\ComfyUI\ComfyUI_windows_portable\python_embeded\Lib\site-packages\huggingface_hub\utils\_validators.py", line 114, in _inner_fn return fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^ File "E:\ComfyUI\ComfyUI_windows_portable\python_embeded\Lib\site-packages\diffusers\configuration_utils.py", line 377, in load_config raise EnvironmentError(
same error have you find any solution
AWESOME!
its working ?
Of course, I tried it myself and you can see in the video that it works
@@CgTopTips i try waiting
Error occurred when executing SVD_img2vid_Conditioning: 'NoneType' object has no attribute 'encode_image' File "E:\comfy UI\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\comfy UI\ComfyUI_windows_portable\ComfyUI\execution.py", line 81, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\comfy UI\ComfyUI_windows_portable\ComfyUI\execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\comfy UI\ComfyUI_windows_portable\ComfyUI\comfy_extras odes_video_model.py", line 46, in encode output = clip_vision.encode_image(init_image) ^^^^^^^^^^^^^^^^^^^^^^^^ svd_ing2vid_Conditioning cannot run ， What is the reason for the error above? Thank you for sharing and looking forward to your reply.
at 9:38 when i queue generation the next ksampler errors with 'NoneType' object has no attribute 'shape', anyone with ideas bout possible issue?
well the object has no attribute error seemed to be due to i neglected to use an sdxl check point (oops) but now i am getting mat1 and mat2 shapes cannot be multiplied (16x2048 and 768x320) error, which i believe may be due to non-matching input image dimensions? should we have a node in here to autoresize input images to keep things smooth?