video-inpainting

Name: video-inpainting
Author: prime-skills

31stars9forks

How to install video-inpainting?

prime-skills/runcomfy-agent-skills/video-inpainting

$npx -y skills add prime-skills/runcomfy-agent-skills --skill video-inpainting

Installs into the current project.

Summary

Region edits across video frames on RunComfy via the runcomfy CLI — remove an object that appears across many frames, clean up wires or watermarks, replace a region with matching motion. Routes across Wan 2-7 edit-video (default, prompt-driven region edits with spatial language

Files · 1

View on GitHub

SKILL.md

1	# Video Inpainting
2
3	Region edits across video frames — remove an object that appears across many frames, clean up wires or watermarks, replace a region with motion that matches the rest of the clip. This skill routes across the prompt-driven video edit endpoints in the RunComfy catalog and gives the agent a clear default for each intent.
4
5	[runcomfy.com](https://www.runcomfy.com/?utm_source=skills.sh&utm_medium=skill&utm_campaign=video-inpainting) · [Wan 2-7 edit-video](https://www.runcomfy.com/models/wan-ai/wan-2-7/edit?utm_source=skills.sh&utm_medium=skill&utm_campaign=video-inpainting) · [CLI docs](https://docs.runcomfy.com/cli/introduction?utm_source=skills.sh&utm_medium=skill&utm_campaign=video-inpainting)
6
7	## Powered by the RunComfy CLI
8
9	```bash
10	# 1. Install (see runcomfy-cli skill for details)
11	npm i -g @runcomfy/cli # or: npx -y @runcomfy/cli --version
12
13	# 2. Sign in
14	runcomfy login # or in CI: export RUNCOMFY_TOKEN=<token>
15
16	# 3. Edit a video (closest CLI-reachable approach)
17	runcomfy run wan-ai/wan-2-7/edit-video \
18	--input '{"video_url": "...", "prompt": "..."}' \
19	--output-dir ./out
20	```
21
22	CLI deep dive: [`runcomfy-cli`](https://www.skills.sh/agentspace-so/runcomfy-agent-skills/runcomfy-cli) skill.
23
24	---
25
26	## Pick the right model
27
28	Routes via prompt-driven region edits — the model resolves the targeted region from spatial language across all frames.
29
30	Wan 2-7 Edit-Video — `wan-ai/wan-2-7/edit-video` (default)
31	> Wan 2-7's video edit endpoint. Drive frame-by-frame edits via prompt + the source video.
32	> Pick for: "remove the watermark in the bottom-right", "replace the sky with a sunset" — prompt-driven region intent without an explicit mask.
33	> Avoid for: precise pixel-level region targeting — use a ComfyUI workflow.
34
35	Lucy Edit Restyle — `decart/lucy-edit/restyle`
36	> Identity-stable video restyle that handles region-aware edits.
37	> Pick for: lightweight outfit / object swap that needs to track across frames.
38	> Avoid for: surgical mask-driven inpaint — ComfyUI workflow.
39
40	Seedream 4-0 Edit-Sequential — [`bytedance/seedream-4-0/edit-sequential`](https://www.runcomfy.com/models/bytedance/seedream-4-0/edit-sequential?utm_source=skills.sh&utm_medium=skill&utm_campaign=video-inpainting)
41	> Sequential still edits — feed a sequence of frames as inputs, apply the same edit instruction across each, useful if you're treating the video as a frame stack.
42	> Pick for: short, low-frame-rate sequences where each frame can be edited independently and a separate tool re-encodes to video.
43	> Avoid for: long clips, motion-coherent fills — temporal consistency degrades.
44
45	---
46
47	## Route 1: Wan 2-7 Edit-Video — closest CLI path
48
49	Model: `wan-ai/wan-2-7/edit-video`
50	Catalog: [Wan 2-7 edit-video](https://www.runcomfy.com/models/wan-ai/wan-2-7/edit?utm_source=skills.sh&utm_medium=skill&utm_campaign=video-inpainting)
51
52	### Invoke
53
54	```bash
55	runcomfy run wan-ai/wan-2-7/edit-video \
56	--input '{
57	"video_url": "https://your-cdn.example/source.mp4",
58	"prompt": "Remove the watermark in the bottom-right corner across all frames. Preserve all other content exactly. Match background where the watermark was."
59	}' \
60	--output-dir ./out
61	```
62
63	### Prompting tips
64
65	- Describe the region in spatial language — `"bottom-right corner"`, `"the cables overhead"`, `"the second person from the left"`.
66	- Lead with preservation: `"Preserve all other content exactly"` — without this Wan may restyle frames inadvertently.
67	- One change per call. Compound edits (remove A and replace B) tend to drift; split into sequential edit passes.
68
69	For broader video edit, see [`video-edit`](https://www.skills.sh/agentspace-so/runcomfy-agent-skills/video-edit).
70
71	---
72
73	## When you need pixel-precise mask propagation
74
75	The endpoints above are prompt-driven — they resolve the target region from spatial language. For pixel-precise mask propagation with SAM2 segmentation tracking + temporal-aware inpaint backfill, Run

People who liked this also viewed

6 picks

Type

video-inpainting

31stars9forks

View on GitHub

How to install video-inpainting?

prime-skills/runcomfy-agent-skills/video-inpainting

$npx -y skills add prime-skills/runcomfy-agent-skills --skill video-inpainting

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Video Inpainting
2
3	Region edits across video frames — remove an object that appears across many frames, clean up wires or watermarks, replace a region with motion that matches the rest of the clip. This skill routes across the prompt-driven video edit endpoints in the RunComfy catalog and gives the agent a clear default for each intent.
4
5	[runcomfy.com](https://www.runcomfy.com/?utm_source=skills.sh&utm_medium=skill&utm_campaign=video-inpainting) · [Wan 2-7 edit-video](https://www.runcomfy.com/models/wan-ai/wan-2-7/edit?utm_source=skills.sh&utm_medium=skill&utm_campaign=video-inpainting) · [CLI docs](https://docs.runcomfy.com/cli/introduction?utm_source=skills.sh&utm_medium=skill&utm_campaign=video-inpainting)
6
7	## Powered by the RunComfy CLI
8
9	```bash
10	# 1. Install (see runcomfy-cli skill for details)
11	npm i -g @runcomfy/cli # or: npx -y @runcomfy/cli --version
12
13	# 2. Sign in
14	runcomfy login # or in CI: export RUNCOMFY_TOKEN=<token>
15
16	# 3. Edit a video (closest CLI-reachable approach)
17	runcomfy run wan-ai/wan-2-7/edit-video \
18	--input '{"video_url": "...", "prompt": "..."}' \
19	--output-dir ./out
20	```
21
22	CLI deep dive: [`runcomfy-cli`](https://www.skills.sh/agentspace-so/runcomfy-agent-skills/runcomfy-cli) skill.
23
24	---
25
26	## Pick the right model
27
28	Routes via prompt-driven region edits — the model resolves the targeted region from spatial language across all frames.
29
30	Wan 2-7 Edit-Video — `wan-ai/wan-2-7/edit-video` (default)
31	> Wan 2-7's video edit endpoint. Drive frame-by-frame edits via prompt + the source video.
32	> Pick for: "remove the watermark in the bottom-right", "replace the sky with a sunset" — prompt-driven region intent without an explicit mask.
33	> Avoid for: precise pixel-level region targeting — use a ComfyUI workflow.
34
35	Lucy Edit Restyle — `decart/lucy-edit/restyle`
36	> Identity-stable video restyle that handles region-aware edits.
37	> Pick for: lightweight outfit / object swap that needs to track across frames.
38	> Avoid for: surgical mask-driven inpaint — ComfyUI workflow.
39
40	Seedream 4-0 Edit-Sequential — [`bytedance/seedream-4-0/edit-sequential`](https://www.runcomfy.com/models/bytedance/seedream-4-0/edit-sequential?utm_source=skills.sh&utm_medium=skill&utm_campaign=video-inpainting)
41	> Sequential still edits — feed a sequence of frames as inputs, apply the same edit instruction across each, useful if you're treating the video as a frame stack.
42	> Pick for: short, low-frame-rate sequences where each frame can be edited independently and a separate tool re-encodes to video.
43	> Avoid for: long clips, motion-coherent fills — temporal consistency degrades.
44
45	---
46
47	## Route 1: Wan 2-7 Edit-Video — closest CLI path
48
49	Model: `wan-ai/wan-2-7/edit-video`
50	Catalog: [Wan 2-7 edit-video](https://www.runcomfy.com/models/wan-ai/wan-2-7/edit?utm_source=skills.sh&utm_medium=skill&utm_campaign=video-inpainting)
51
52	### Invoke
53
54	```bash
55	runcomfy run wan-ai/wan-2-7/edit-video \
56	--input '{
57	"video_url": "https://your-cdn.example/source.mp4",
58	"prompt": "Remove the watermark in the bottom-right corner across all frames. Preserve all other content exactly. Match background where the watermark was."
59	}' \
60	--output-dir ./out
61	```
62
63	### Prompting tips
64
65	- Describe the region in spatial language — `"bottom-right corner"`, `"the cables overhead"`, `"the second person from the left"`.
66	- Lead with preservation: `"Preserve all other content exactly"` — without this Wan may restyle frames inadvertently.
67	- One change per call. Compound edits (remove A and replace B) tend to drift; split into sequential edit passes.
68
69	For broader video edit, see [`video-edit`](https://www.skills.sh/agentspace-so/runcomfy-agent-skills/video-edit).
70
71	---
72
73	## When you need pixel-precise mask propagation
74
75	The endpoints above are prompt-driven — they resolve the target region from spatial language. For pixel-precise mask propagation with SAM2 segmentation tracking + temporal-aware inpaint backfill, Run

People who liked this also viewed

6 picks

Type