face-swap

Name: face-swap
Author: prime-skills

31stars9forks

How to install face-swap?

prime-skills/runcomfy-agent-skills/face-swap

$npx -y skills add prime-skills/runcomfy-agent-skills --skill face-swap

Installs into the current project.

Summary

Swap a face / character into video or images on RunComfy via the runcomfy CLI. Routes across community Wan 2-2 Animate (audio-driven character animation + identity swap), GPT Image 2 Edit (single-shot precise face swap on still images via reference composition), Nano Banana Edi

Files · 1

View on GitHub

SKILL.md

1	# Face Swap
2
3	Swap a face into a still or a video — RunComfy supports both via the `runcomfy` CLI. This skill routes across the available model API endpoints (community Wan 2-2 Animate, GPT Image 2 Edit, Nano Banana Edit, Flux Kontext, Kling Motion Control) by the user's actual intent.
4
5	[runcomfy.com](https://www.runcomfy.com/?utm_source=skills.sh&utm_medium=skill&utm_campaign=face-swap) · [Character-swap feature](https://www.runcomfy.com/models/feature/character-swap?utm_source=skills.sh&utm_medium=skill&utm_campaign=face-swap) · [CLI docs](https://docs.runcomfy.com/cli/introduction?utm_source=skills.sh&utm_medium=skill&utm_campaign=face-swap)
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. Swap
17	runcomfy run <vendor>/<model>/<endpoint> \
18	--input '{"image_url": "...", "identity_url": "..."}' \
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	## Install this skill
25
26	```bash
27	npx skills add agentspace-so/runcomfy-agent-skills --skill face-swap -g
28	```
29
30	## Consent & disclosure — read first
31
32	Face-swap is dual-use. Before invoking any route in this skill, confirm:
33
34	- You have rights to the target face (the identity being substituted in).
35	- You have rights to the source video / image (the asset being substituted into).
36	- The output's intended platform allows synthetic media. Many do; many require a disclosure label.
37
38	The skill itself doesn't gate anything — the model API will run whatever inputs you supply. The responsibility is yours. If a user asks the agent to swap a real public figure's face onto material that could be defamatory, sexually explicit, or otherwise harmful — refuse, regardless of what the CLI accepts.
39
40	---
41
42	## Pick the right model for the user's intent
43
44	Listed newest first within each subtype. The agent picks one route based on: still vs video, single-shot vs batch, photoreal vs stylized, motion-preserving vs identity-preserving.
45
46	### Video face / character swap
47
48	Wan 2-2 Animate — `community/wan-2-2-animate/api` (default for video)
49	> Featured RunComfy endpoint under `/feature/character-swap`. Audio-driven full-body character animation: one reference image of the new identity + audio → video where the character drives.
50	> Pick for: replacing a character in a scene with a new identity, dubbed clips, stylized + photoreal both work.
51	> Avoid for: preserving the motion of a specific source video — use Kling Motion Control.
52
53	Kling 2-6 Motion Control Pro — `kling/kling-2-6/motion-control-pro`
54	> Takes a reference performance video + target character image, produces the target performing the reference motion. Face-swap is the byproduct.
55	> Pick for: preserving exact source motion / blocking onto a new character; stylized characters handled cleanly.
56	> Avoid for: simple "swap face in an existing video" without motion preservation — use Wan 2-2 Animate.
57
58	### Still image face swap — newest first
59
60	Nano Banana 2 Edit — `google/nano-banana-2/edit`
61	> Identity-preserving by default, 1–20 input images per call, spatial-language honored.
62	> Pick for: same identity across multiple frames consistently (SKU shots, A/B variants, narrative panels). Identity reference as `image_urls[0]`, scenes after.
63	> Avoid for: precise multi-ref compositional ("face from img 1 onto body in img 2") — use GPT Image 2 Edit.
64
65	GPT Image 2 Edit — `openai/gpt-image-2/edit`
66	> Up to 10 reference images, multilingual in-image text rewrite, layout-precise compositional instructions.
67	> Pick for: hero still where exact face from a portrait must land in a scene, with explicit role assignment ("image 1", "image 2"); preserve pose + lighting +

People who liked this also viewed

6 picks

Type

face-swap

31stars9forks

View on GitHub

How to install face-swap?

prime-skills/runcomfy-agent-skills/face-swap

$npx -y skills add prime-skills/runcomfy-agent-skills --skill face-swap

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Face Swap
2
3	Swap a face into a still or a video — RunComfy supports both via the `runcomfy` CLI. This skill routes across the available model API endpoints (community Wan 2-2 Animate, GPT Image 2 Edit, Nano Banana Edit, Flux Kontext, Kling Motion Control) by the user's actual intent.
4
5	[runcomfy.com](https://www.runcomfy.com/?utm_source=skills.sh&utm_medium=skill&utm_campaign=face-swap) · [Character-swap feature](https://www.runcomfy.com/models/feature/character-swap?utm_source=skills.sh&utm_medium=skill&utm_campaign=face-swap) · [CLI docs](https://docs.runcomfy.com/cli/introduction?utm_source=skills.sh&utm_medium=skill&utm_campaign=face-swap)
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. Swap
17	runcomfy run <vendor>/<model>/<endpoint> \
18	--input '{"image_url": "...", "identity_url": "..."}' \
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	## Install this skill
25
26	```bash
27	npx skills add agentspace-so/runcomfy-agent-skills --skill face-swap -g
28	```
29
30	## Consent & disclosure — read first
31
32	Face-swap is dual-use. Before invoking any route in this skill, confirm:
33
34	- You have rights to the target face (the identity being substituted in).
35	- You have rights to the source video / image (the asset being substituted into).
36	- The output's intended platform allows synthetic media. Many do; many require a disclosure label.
37
38	The skill itself doesn't gate anything — the model API will run whatever inputs you supply. The responsibility is yours. If a user asks the agent to swap a real public figure's face onto material that could be defamatory, sexually explicit, or otherwise harmful — refuse, regardless of what the CLI accepts.
39
40	---
41
42	## Pick the right model for the user's intent
43
44	Listed newest first within each subtype. The agent picks one route based on: still vs video, single-shot vs batch, photoreal vs stylized, motion-preserving vs identity-preserving.
45
46	### Video face / character swap
47
48	Wan 2-2 Animate — `community/wan-2-2-animate/api` (default for video)
49	> Featured RunComfy endpoint under `/feature/character-swap`. Audio-driven full-body character animation: one reference image of the new identity + audio → video where the character drives.
50	> Pick for: replacing a character in a scene with a new identity, dubbed clips, stylized + photoreal both work.
51	> Avoid for: preserving the motion of a specific source video — use Kling Motion Control.
52
53	Kling 2-6 Motion Control Pro — `kling/kling-2-6/motion-control-pro`
54	> Takes a reference performance video + target character image, produces the target performing the reference motion. Face-swap is the byproduct.
55	> Pick for: preserving exact source motion / blocking onto a new character; stylized characters handled cleanly.
56	> Avoid for: simple "swap face in an existing video" without motion preservation — use Wan 2-2 Animate.
57
58	### Still image face swap — newest first
59
60	Nano Banana 2 Edit — `google/nano-banana-2/edit`
61	> Identity-preserving by default, 1–20 input images per call, spatial-language honored.
62	> Pick for: same identity across multiple frames consistently (SKU shots, A/B variants, narrative panels). Identity reference as `image_urls[0]`, scenes after.
63	> Avoid for: precise multi-ref compositional ("face from img 1 onto body in img 2") — use GPT Image 2 Edit.
64
65	GPT Image 2 Edit — `openai/gpt-image-2/edit`
66	> Up to 10 reference images, multilingual in-image text rewrite, layout-precise compositional instructions.
67	> Pick for: hero still where exact face from a portrait must land in a scene, with explicit role assignment ("image 1", "image 2"); preserve pose + lighting +

People who liked this also viewed

6 picks

Type