Wan VACE Erase, Add Objects
Invitation Code 【rh v1312】
https://www.runninghub.cn/?inviteCode=rh v1312
Use this code to receive a reward of 1000 RH coins (approximately enough for running over 20 videos and hundreds of images).

Use depth or pose maps to control video generation

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

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

Features:
1. Recognize as rectangular mask: Generates a rectangular mask based on the items you input for removal.
2. Precise mask recognition: Generates a precise mask based on the items you input for removal.
3. Enable reference image: Generates corresponding items based on the reference image you upload.
4. Recognize main subject and crop: Only works for images with a main subject; may produce errors for scenes.

Parameters:
1. Random seed: Changing the random seed will alter the generated results.
2. Limit resolution: The maximum width and height of the image/video will not exceed the set value, and the other side will scale proportionally.
3. Skip how many initial frames of the video: Controls based on the original frame count of the video. For example, if the original video is 30 frames per second, setting this to 30 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 a frame rate of 16 frames per second, resulting in a 5-second video.
5. Positive prompts: Words that control the generation of images/videos. Provide reasonable descriptions based on the uploaded image.



Note:

1. The force_rate of the **Load Video** node determines the frames per second of the video. Inputting 16 means 16 frames per second.

2. The frame_load_cap and skip_first_frames of the **Load Video** node are only for preview references.
The final decision on skipping frames and generating video frames is determined by the green parameter button.

3. Save location

Videos will be saved in the "output/videos" folder.

4. Video acceleration

If your comfyui does not have triton and sageattn installed, please delete
WanVideo Torch Compile Settings in wan2.1 video generation.
Change the attention_mode of WanVideo Model Loader to sdpa.
Otherwise, errors may occur.

If your GPU memory is low and cannot generate, you can set blocks_to_swap to 30~40 in WanVideo BlockSwap. Although slower, at least it can generate.

You can also join Ashuo's member group. WeChat: yumengashuo
The community provides:
1. Exclusive advanced workflows for comfyui
2. Solutions to various difficult problems
3. Ashuo's integrated package to resolve environment conflicts and 100 original workflows
4. The latest AI news from abroad
5. Community Q&A support