Add Wan-FUN Camera Control models and Add WanCameraImageToVideo node #8013
Conversation
|
I uploaded two different versions of quantization models to the community. |
|
You wrote two hyperlinks tha points to the same model Is the other one this one ? There are also two other models that are the same but without the camera word (just 1.3B-Control and 14B-Control) |
Yep sorry, it should be https://huggingface.co/alibaba-pai/Wan2.1-Fun-V1.1-14B-Control-Camera and https://huggingface.co/alibaba-pai/Wan2.1-Fun-V1.1-1.3B-Control-Camera |
|
I don't think the camera_conditions should be of type LATENT because it's confusing, it should be a different type like WAN_CAMERA_EMBEDDING. Can you also make it an optional input like the start image? You should also include a node that can generate some basic camera_conditions in this pr. |
|
I don't think the camera_conditions should be of type LATENT because it's confusing, it should be a different type like WAN_CAMERA_EMBEDDING. Can you also make it an optional input like the start image? You should also include a node that can generate some basic camera_conditions in this pr. I have updated the code based on your suggestions. |
…huawei * 'master' of https://github.com/zhiaixu2009/ComfyUI: Fix typo in last PR. (comfyanonymous#8144) Add Wan-FUN Camera Control models and Add WanCameraImageToVideo node (comfyanonymous#8013) Remove old hack used to fix windows pytorch 2.4 on the portable. (comfyanonymous#8139) Add `get_duration` method to Comfy VIDEO type (comfyanonymous#8122)
VideoX-Fun recently released two models for camera control, Wan2.1-Fun-V1.1-1.3B-Control-Camera and Wan2.1-Fun-V1.1-14B-Control-Camera.
To support these two models, I add a new node WanCameraImageToVideo, for customizing inputs for camera control models.
I also added a node VideoAcc_CameraTrajectoryRecam to calculate Plücker embeddings as the input of WanCameraImageToVideo node, in my customized node repo.
Here I attached the JSON workflow for your reference.
wan2.1_fun_Camera_Control.json