LatentSync and LTX version has LTX for video and LatenSync for Lip sync, fastest video and lip sync options.
Other versions are more resource intensive but offer better quality using Sonic for Lip sync and Hunyuan or Wan for video.
If you have a lower end gpu try the LTX and LatentSync version, Higher end cards try the other versions.
if you downloaded the workflow previously, you may need to delete red nodes and re-add them.
Kokoro TTS Custom Node, with Flux Schnell and Sonic to make Talking Head Style videos. pip install kokoro==0.8.4 to avoid the safe-pickle issue.
Article for newest version.
https://civarchive.com/articles/12337/geeky-kokoro-tts-animation-station
Description
FAQ
Comments (5)
Will it work with 16gb on a 4060Ti?
It should? I use a laptop 4090 which only has 16gb of vram. Do each step separately though.
So I have everything downloaded. I followed the file structure provided at:
https://github.com/smthemex/ComfyUI_Sonic/tree/main?tab=readme-ov-file
I am not sure what "SONIC_PreData" is
Thanks.
ComfyUI Error Report ## Error Details - **Node ID:** 112 - **Node Type:** SONIC_PreData - **Exception Type:** Exception - **Exception Message:** Please download the model first ## Stack Trace ``` File "/workspace/ComfyUI/execution.py", line 327, in execute output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/workspace/ComfyUI/execution.py", line 202, in get_output_data return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/workspace/ComfyUI/custom_nodes/comfyui-0246/utils.py", line 353, in new_func res_value = old_func(*final_args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/workspace/ComfyUI/execution.py", line 174, in _map_node_over_list process_inputs(input_dict, i) File "/workspace/ComfyUI/execution.py", line 163, in process_inputs results.append(getattr(obj, func)(**inputs)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/workspace/ComfyUI/custom_nodes/ComfyUI_Sonic/sonic_node.py", line 141, in sampler_main raise Exception("Please download the model first")
The error message is likely due to missing models.
Make sure you followed the instructions on the readme and download these models and place them in the correct locations.
3.Model
3.1.1 download checkpoints from google 从Google下载必须的模型,文件结构如下图
3.1.2 download openai/whisper-tiny
-- ComfyUI/models/sonic/ |-- audio2bucket.pth |-- audio2token.pth |-- unet.pth |-- yoloface_v5m.pt |-- whisper-tiny/ |--config.json |--model.safetensors |--preprocessor_config.json |-- RIFE/ |--flownet.pkl3.2 SVD checkpoints svd_xt.safetensors or svd_xt_1_1.safetensors
-- ComfyUI/models/checkpoints ├── svd_xt.safetensors or svd_xt_1_1.safetensorsThe sonic repo isn't mine, it's one I've incorporated into my workflow so my troubleshooting help will be limited. If this continues to give issues, you can try latensync as an alternative. It's a bit faster but the quality isn't as good and it has it's own issues.