Skip to main content
The WanSCAILToVideo node prepares conditioning and an empty latent space for video generation. It processes optional inputs like reference images, pose videos, CLIP vision outputs, and previous frame chunks, embedding them into the positive and negative conditioning for a video model. The node outputs the modified conditioning and a blank latent tensor of the specified video dimensions.

Inputs

ParameterDescriptionData TypeRequiredRange
positiveThe positive conditioning input.CONDITIONINGYes-
negativeThe negative conditioning input.CONDITIONINGYes-
vaeThe VAE model used for encoding images and video frames.VAEYes-
widthThe width of the output video in pixels (default: 512). Must be divisible by 32.INTYes32 to MAX_RESOLUTION
heightThe height of the output video in pixels (default: 896). Must be divisible by 32.INTYes32 to MAX_RESOLUTION
lengthThe number of frames in the video (default: 81). Must be divisible by 4.INTYes1 to MAX_RESOLUTION
batch_sizeThe number of videos to generate in a batch (default: 1).INTYes1 to 4096
pose_videoVideo used for pose conditioning. Will be downscaled to half the resolution of the main video.IMAGENo-
pose_video_maskSCAIL-2 only. Colored per-identity SAM3 mask video at the same resolution as pose_video.IMAGENo-
replacement_modeSCAIL-2 only. False = Animation Mode (pose_video_mask should have black background). True = Replacement Mode (pose_video_mask should have white background). Default: False.BOOLEANNo-
pose_strengthStrength of the pose latent (default: 1.0).FLOATYes0.0 to 10.0
pose_startStart step of the pose conditioning (default: 0.0).FLOATYes0.0 to 1.0
pose_endEnd step of the pose conditioning (default: 1.0).FLOATYes0.0 to 1.0
reference_imageReference image, for multiple references composite all on single image.IMAGENo-
reference_image_maskSCAIL-2 only. Colored reference mask at the same resolution as reference_image.IMAGENo-
clip_vision_outputCLIP vision features for conditioning. Model is trained with stretch resize to aspect ratio.CLIP_VISION_OUTPUTNo-
video_frame_offsetCumulative output frame this chunk begins at. Wire from the previous chunk’s video_frame_offset output (default: 0).INTYes0 to MAX_RESOLUTION
previous_frame_countTail frames of previous_frames to anchor. SCAIL-2 trained at 5 (81-frame chunks, 76-frame step) (default: 5).INTYes1 to MAX_RESOLUTION
previous_framesSCAIL-2 only. Full decoded output of the previous chunk. Only the last previous_frame_count are used as the extension anchor.IMAGENo-
Note: The pose_video and pose_video_mask inputs are processed only for the first length frames. The reference_image is processed only for the first image in the batch. When reference_image is provided, it is encoded into a latent and embedded into both positive and negative conditioning. When clip_vision_output is provided, it is applied to both positive and negative conditioning. The pose_video is downscaled to half the resolution of the main video before encoding. When previous_frames is provided, only the last previous_frame_count frames are used as the extension anchor, and the video_frame_offset is adjusted accordingly. In Replacement Mode (replacement_mode=True), the reference image is composited on a black background using the reference image mask as an alpha matte.

Outputs

Output NameDescriptionData Type
positiveThe modified positive conditioning, potentially containing embedded reference image latents, CLIP vision output, pose video latents, driving masks, reference masks, or previous frame latents.CONDITIONING
negativeThe modified negative conditioning, potentially containing embedded reference image latents, CLIP vision output, pose video latents, driving masks, reference masks, or previous frame latents.CONDITIONING
latentAn empty latent tensor of shape [batch_size, 16, ((length - 1) // 4) + 1, height // 8, width // 8]. When previous_frames is provided, the latent is partially filled with encoded previous frames and a noise mask is included.LATENT
video_frame_offsetAdjusted offset + length. Wire into the next chunk for sequential video generation.INT
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

Source fingerprint (SHA-256): 30e14959248c46e624e2ce2e3d079cd5aad94c12b66d74d4979ef70143b871e3