Save 4 hours! We auto-setup your workflow! Free!

Drop your workflow.json — we handle every dependency, custom node, and model. Just open the link and run.

Auto-Setup Workflow Json (Free) Now!
ComfyUI > Nodes > comfyui-slapshot > Slapshot — Rotoscoping

ComfyUI Node: Slapshot — Rotoscoping

Class Name

Slapshot_Rotoscoping

Category
Slapshot
Author
slapshot-ai (Account age: 0days)
Extension
comfyui-slapshot
Latest Updated
2026-11-03
Github Stars
0.0K

How to Install comfyui-slapshot

Install this extension via the ComfyUI Manager by searching for comfyui-slapshot
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter comfyui-slapshot in the search bar
After installation, click the Restart button to restart ComfyUI. Then, manually refresh your browser to clear the cache and access the updated list of nodes.

Visit ComfyUI Online for ready-to-use ComfyUI environment

  • Free trial available
  • 16GB VRAM to 80GB VRAM GPU machines
  • 400+ preloaded models/nodes
  • Freedom to upload custom models/nodes
  • 200+ ready-to-run workflows
  • 100% private workspace with up to 200GB storage
  • Dedicated Support

Run ComfyUI Online

Slapshot — Rotoscoping Description

Uploads video and optional masks for Slapshot rotoscoping; completion is reported by email.

Slapshot — Rotoscoping:

Slapshot_Rotoscoping submits a video to the Slapshot service for rotoscoping, the process of identifying and separating a subject across video frames. You can provide reference masks to indicate the areas you want the service to follow. The node uploads the source material, starts a remote job, and displays progress while it waits for inference to finish. Processing requires a Slapshot API key and a network connection. When the job completes, the node displays a completion message directing you to check your email; it does not place a processed video or mask sequence into the ComfyUI workflow.

Slapshot — Rotoscoping Input Parameters:

video

The required VIDEO input is the clip you want to process. Connect a compatible ComfyUI video source with a resolvable file or a working save_to() method. The node accepts .mp4 and .mov files, checks that it can determine a positive frame count, and rejects clips longer than 3,500 frames. Video length also affects the free-tier limit check. Options: .mp4 or .mov. Minimum: 1 detectable frame. Maximum: 3,500 frames. Default: none; you must connect a video.

mask_00

An optional IMAGE reference mask for a video frame. If it comes directly from LoadImage or Slapshot_Load_Mask, a filename such as 00014.png identifies zero-based frame 14; otherwise, this connected mask receives a sequential fallback frame number. The node uses only the first image if you supply a batch, converts it to a red-on-black PNG, and uploads it as a reference. Options: connect an IMAGE or leave it disconnected. Frame range: 0 through the video’s last frame. Default: disconnected.

mask_01

An optional IMAGE reference mask, handled the same way as mask_00. Its source filename determines its target frame when available; otherwise, the node assigns the next sequential fallback number among connected masks whose filenames cannot be determined. Only the first image in a batch is used. Options: connect an IMAGE or leave it disconnected. Frame range: 0 through the video’s last frame. Default: disconnected.

mask_02

An optional IMAGE reference mask for another frame. A recognized, five-digit PNG filename supplies the zero-based frame number; without one, this mask receives the next sequential fallback number. The mask is uploaded as a red-on-black reference image, using only the first image from a batch. Options: connect an IMAGE or leave it disconnected. Frame range: 0 through the video’s last frame. Default: disconnected.

mask_03

An optional IMAGE reference mask. Use a correctly numbered source PNG when you need this mask to correspond to a specific video frame; otherwise, the node uses its sequential fallback numbering. Only the first image in a batch is uploaded. Options: connect an IMAGE or leave it disconnected. Frame range: 0 through the video’s last frame. Default: disconnected.

mask_04

An optional IMAGE reference mask that provides another frame-specific reference to the remote job. Its recognized source filename sets the frame number, or the node assigns a sequential fallback number if it cannot find one. Only the first image in a batch is used. Options: connect an IMAGE or leave it disconnected. Frame range: 0 through the video’s last frame. Default: disconnected.

mask_05

An optional IMAGE reference mask. Connect it when you have an additional frame to guide rotoscoping; the numbered source filename identifies that frame when available. Without a recognized filename, sequential fallback numbering applies. Only the first image in a batch is used. Options: connect an IMAGE or leave it disconnected. Frame range: 0 through the video’s last frame. Default: disconnected.

mask_06

An optional IMAGE reference mask for an additional video frame. The node uses its recognized five-digit PNG filename to select the target frame, or assigns a sequential fallback number when the filename is unavailable. Only the first image in a batch is uploaded. Options: connect an IMAGE or leave it disconnected. Frame range: 0 through the video’s last frame. Default: disconnected.

mask_07

An optional IMAGE reference mask. As with the other mask sockets, a recognized filename maps it to a specific zero-based frame, while an unavailable filename triggers sequential fallback numbering. The node uses only the first image from a batch. Options: connect an IMAGE or leave it disconnected. Frame range: 0 through the video’s last frame. Default: disconnected.

mask_08

An optional IMAGE reference mask that adds another uploaded reference for the rotoscoping job. Give its source image a five-digit PNG frame filename when precise placement matters; otherwise, the node assigns a fallback frame number. Only the first image in a batch is used. Options: connect an IMAGE or leave it disconnected. Frame range: 0 through the video’s last frame. Default: disconnected.

mask_09

The tenth optional IMAGE reference mask. It follows the same filename-based or sequential fallback frame assignment as the preceding mask sockets, and only its first image is uploaded if you connect a batch. Options: connect an IMAGE or leave it disconnected. Frame range: 0 through the video’s last frame. Default: disconnected.

Slapshot — Rotoscoping Output Parameters:

There are no output sockets. This is an output node: after the remote job completes, it shows a completion message and job information in its UI, but it does not return a processed video, mask, or other value for downstream nodes.

Slapshot — Rotoscoping Usage Tips:

  • Configure SLAPSHOT_API_KEY in .env or config.ini and restart ComfyUI before running the node.
  • Use a .mp4 or .mov video with no more than 3,500 detectable frames. A shorter test clip can help you confirm the setup before submitting a longer job.
  • To target a particular frame, load a PNG named with its zero-based, five-digit frame number, such as 00014.png for frame 14, through LoadImage or Slapshot_Load_Mask. Keep the number within the clip’s frame range.
  • Use separate connections for separate reference frames; each mask socket processes only the first image of an attached batch.
  • Make the intended masked area clearly non-black. The node converts image brightness into a red-on-black reference, so a faint or dark area may not survive conversion as intended.
  • Watch the node’s progress text while uploading and processing. On completion, check your email as directed by the node; do not expect an output socket to appear.

Slapshot — Rotoscoping Common Errors and Solutions:

No API key configured. Set SLAPSHOT_API_KEY in your .env file or config.ini and restart ComfyUI.

  • Explanation: The node cannot find the API key it needs to contact Slapshot.
  • Solution: Add a valid SLAPSHOT_API_KEY to .env or config.ini, then restart ComfyUI.

Invalid or unauthorized API key (401 or 403).

  • Explanation: The service rejected the configured key during upload authorization, the limit check, or job submission.
  • Solution: Check that the key is complete, active, and authorized for the service, then restart ComfyUI if you changed the configuration.

Unsupported video extension. Only .mp4 and .mov are allowed.

  • Explanation: The node cannot identify a supported video filename or finds an unsupported file extension.
  • Solution: Supply a compatible .mp4 or .mov video source. Ensure the connected video exposes its filename and can be saved or resolved to a file.

VIDEO input does not expose save_to() or a resolvable path; upgrade ComfyUI or use a compatible VIDEO source.

  • Explanation: The node cannot obtain a local video file to upload.
  • Solution: Try a video-loading node that provides a resolvable source file, or use a compatible ComfyUI video source.

Input video has no frames, Check input video.

  • Explanation: The node could not determine a positive frame count; this does not necessarily mean the file is visually empty.
  • Solution: Confirm the clip plays correctly, then try a valid .mp4 or .mov file whose frames can be read by your environment.

Input video should not exceed 3500 frames (got N).

  • Explanation: The clip exceeds this node’s 3,500-frame maximum.
  • Solution: Trim or split the clip so each submitted video has at most 3,500 frames.

Mask 'NNNNN.png' targets frame N but the video only has N frame(s).

  • Explanation: A mask’s numbered filename, or its assigned fallback number, points beyond the final video frame.
  • Solution: Check the video’s length and use a five-digit filename within the zero-based range shown in the error. If fallback numbering caused the mismatch, connect a correctly named PNG from LoadImage or Slapshot_Load_Mask.

Mask 'filename' connected to 'mask_XX' does not follow the required naming pattern.

  • Explanation: A directly connected LoadImage or Slapshot_Load_Mask source has a filename that does not match the required five-digit frame-number PNG pattern.
  • Solution: Rename the source image to a name such as 00014.png and reload it. The number must identify an existing frame in the video.

Free tier limit of 1000 frames has been reached.

  • Explanation: The service’s limit response reports that the account is already above its free-tier allowance.
  • Solution: Check the account’s usage and plan; upgrade if you need to continue submitting jobs.

Failed to run workflow. Running this workflow will breach the free tier limit of 1000 frames.

  • Explanation: The reported frames already processed plus this video’s frames meet or exceed the node’s free-tier threshold.
  • Solution: Use a shorter clip where appropriate, or upgrade the account before submitting the job.

Failed to get upload URL or Failed to upload a file.

  • Explanation: The node could not obtain an upload destination or the video or mask upload failed.
  • Solution: Check your network connection and API key, then retry. If the problem persists, retain the full error message for support.

Missing upload_url or s3_key in upload response.

  • Explanation: The upload service responded without the information the node needs to transfer a file.
  • Solution: Retry later; if it continues, report the full response error to the service provider.

Cannot reach the service or Job submission timed out.

  • Explanation: The node could not establish a connection to the job service or did not receive a response in time.
  • Solution: Check your internet connection and any firewall or proxy settings, then retry.

Unexpected response — no job_id.

  • Explanation: The service answered the submission request but did not provide a job identifier, so the node cannot track the job.
  • Solution: Retry later and report the error if it repeats.

Status check failed (HTTP code).

  • Explanation: The service rejected a request to check the running job’s status.
  • Solution: Verify your API key and network connection. If the error persists, keep the displayed job information for support.

Job did not complete within 10 hours.

  • Explanation: The node stopped waiting after its maximum polling period; this message alone does not establish the remote job’s final outcome.
  • Solution: Check the job’s status through the service before submitting it again.

Inference failed — N failed, N cancelled out of N.

  • Explanation: The remote job finished without any completed work items.
  • Solution: Review the submitted video and masks, then retry. If the failure repeats, provide the job identifier to support.

Job cancelled.

  • Explanation: Processing was interrupted. If the remote job had already been submitted, the node requests its cancellation.
  • Solution: Run the workflow again when you are ready, and check the remote job’s status if cancellation occurred after submission.

Slapshot — Rotoscoping Related Nodes

Go back to the extension to check out more related nodes.
comfyui-slapshot
RunComfy
Copyright 2025 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.

Slapshot — Rotoscoping