ComfyUI Node
Difforum · Guide Frames
Warp one anchor image along the Director's camera path. Produces a guide video whose motion is exactly the camera you drew, for video models that take control/guide frames (LTX guides, Wan VACE, H3 first/last frame). Revealed areas are filled with neutral gray and marked in the mask, using the convention the target expects.
Difforum · Guide Frames
- anchor_image
- direction
- params
- camera
- depth
- guide_frames
- masks
- info
◄mask_convention1 = generate (VACE / LTX / H3)►
◄hole_fillgray►
◄translation_scale1.00►
CategoryDifforum/5 · Video model bridges
Inputs (8)
| Name | Type | Default | Description |
|---|---|---|---|
| anchor_image | IMAGE | The image the camera travels over (usually your first frame). | |
| mask_convention | COMBO | 1 = generate (VACE / LTX / H3) | Which value the mask uses for 'generate': 1 = generate (VACE / LTX / H3 / Fill Reveal) or 1 = keep. |
| hole_fill | COMBO | gray | What goes into the area the camera uncovers before AI fills it: gray (neutral, best for Fill Reveal and H3), stretched edge, or black. |
| directionopt | DIFFORUM_DIRECTION | The Director's wire: camera, energy curve, scene prompts, keys and look in one cable. | |
| paramsopt | DIFFORUM_PARAMS | From Setup: frame count, fps, width and height. Plug the same Setup everywhere. | |
| cameraopt | DIFFORUM_CAMERA | A camera track from Camera (keys), Camera (expressions) or Camera Import. Overrides the Director's camera. | |
| depthopt | IMAGE | Depth of the anchor, for real parallax in 3d mode. | |
| translation_scaleopt | FLOAT | 1.000–20 | Strength of 3D translation vs. the depth range. |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| guide_frames | IMAGE | — |
| masks | MASK | — |
| info | STRING | — |