Wan VACE erase, add objects

Use depth or pose maps to control video generation

Usage 1:
1. Load video
2. Enable control function
3. Enter prompts
4. Generate

Usage 2:
1. Load video
2. Enable reference image function
3. Load reference image
4. Enable control function
5. Enter prompts
6. Generate

Functions:
1. Recognize as rectangular mask: Generate rectangular masks based on the items you input to remove
2. Precisely recognize masks: Generate precise masks based on the items you input to remove
3. Enable reference images: Generate corresponding objects based on the reference images you upload
4. Recognize subject and cut out: Subject images can be recognized, but errors may occur for scenes

Parameters:
1. Random seed: Changing the random seed will alter the generated result
2. Resolution limit: The maximum width and height of images/videos won't exceed the set value, with the other side scaled proportionally
3. Skip how many frames at the start of the video: Controlled based on the original frame count of the video. For example, if the original video has 30 frames per second, setting 30 here will skip the first second
4. Duration of generated video: Set based on the video model. For example, the official example of wan2.1 generates 81 frames with 16 frames per second, resulting in a 5-second video
5. Positive prompts: Control the words for generating images/videos and input reasonable descriptions based on the uploaded images

Note:

1. **Load video** node's force_rate determines the video's frames per second. Input 16 for 16 frames per second

2. **Load video** node's frame_load_cap and skip_first_frames are only for preview reference
The final decision on skipped frames and generated video frames is controlled by the green parameter buttons

3. Save location
Videos will be saved in the "output/video" folder

4. Video acceleration
If your comfyui does not have triton and sageattn installed, please delete
WanVideo Torch Compile Settings from wan2.1 image-to-video
Change WanVideo Model Loader's attention_mode to sdpa
Otherwise, errors will occur

If you have low VRAM and cannot generate, you can set blocks_to_swap to 30~40 in WanVideo BlockSwap. Although slower, it will at least generate

You can also join Ashuo's Knowledge Planet ID: 17259412
Direct link: https://t.zsxq.com/TIfva
Community provides:
1. Exclusive advanced workflows for comfyui
2. Solutions for various problems
3. Ashuo's integration package to resolve environment conflicts, including 100 original workflows
4. Latest overseas AI news
5. Community Q&A support