MeshGraphormer Hand Refiner | txt2img & img2img Workflow
Added 2024-01-19 19:16:27 +0000 UTCAbout This Workflow :
The tutorial features a comprehensive workflow diagram that guides you through the entire process of refining hands in images using the MeshGraphormer Hand Refiner. The diagram showcases a step-by-step approach, starting with loading the default text-to-image or image-to-image workflow, depending on your requirements. It highlights the key components such as the ControlNet Custom Node, ComfyUI's ControlNet Auxiliary Preprocessors, and the MeshGraphormer Hand Refiner. By following the diagram, you can easily understand the flow of data and the connections between different nodes and parameters. This visual representation ensures a smooth and efficient execution of the workflow, allowing you to achieve impressive results in refining and enhancing hand details in your images.
Workflow JSON Attachment Below.
Comments
This is not trained based on SDXL.
Benjamin Law
2024-08-01 14:47:26 +0000 UTCSorry to revive this, but is there a work around to make it work with XL models? I just have XL models from the client IP.
Mauricio Tonon
2024-08-01 13:32:10 +0000 UTCInnovate Futures @ Benji I wasn't sure if you've seen my comment here. Would you happen to know how to fix this?
Urban Avenue
2024-02-27 06:21:33 +0000 UTCNew problem though, I received the following error. Do you have any insight on how to fix this: "Error occurred when executing KSampler: #### It seems that models and clips are mixed and interconnected between SDXL Base, SDXL Refiner, SD1.x, and SD2.x. Please verify. ####"
Urban Avenue
2024-02-22 09:57:58 +0000 UTCCUDA problem , have you did anything with you OS or Kerrnel before?
Benjamin Law
2024-02-22 05:58:10 +0000 UTCI get the following error when running your worlflow, do you know how I can fix this: "Error occurred when executing VAEEncode: CUDA error: the launch timed out and was terminated CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions."
Urban Avenue
2024-02-22 04:49:22 +0000 UTCHi, you may want to check out this tutorial first https://www.patreon.com/posts/96814372?utm_campaign=postshare_creator
Benjamin Law
2024-02-03 05:12:47 +0000 UTChow do i get the custom node for this? MeshGraphormer-DepthMapPreprocessor
Will Reynolds
2024-02-02 23:01:40 +0000 UTC
