controlnet-pose

Name: controlnet-pose
Author: prime-skills

31stars9forks

How to install controlnet-pose?

prime-skills/runcomfy-agent-skills/controlnet-pose

$npx -y skills add prime-skills/runcomfy-agent-skills --skill controlnet-pose

Installs into the current project.

Summary

Pose-conditioned generation on RunComfy via the runcomfy CLI. Routes across Kling 2-6 Motion Control Pro / Standard (transfer the motion / blocking of a reference video onto a target character), community Wan 2-2 Animate (audio-driven character animation with pose conditioning)

Files · 1

View on GitHub

SKILL.md

1	# ControlNet & Pose
2
3	Condition image or video generation on a pose, skeleton, or motion reference. This skill routes across the pose-driven Model API endpoints reachable today and points the agent at ComfyUI workflows for richer ControlNet rigs.
4
5	[runcomfy.com](https://www.runcomfy.com/?utm_source=skills.sh&utm_medium=skill&utm_campaign=controlnet-pose) · [Kling motion control](https://www.runcomfy.com/models/kling/kling-2-6/motion-control-pro?utm_source=skills.sh&utm_medium=skill&utm_campaign=controlnet-pose) · [CLI docs](https://docs.runcomfy.com/cli/introduction?utm_source=skills.sh&utm_medium=skill&utm_campaign=controlnet-pose)
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. Pose-conditioned generate
17	runcomfy run <vendor>/<model> \
18	--input '{"reference_video_url": "...", "character_image_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	---
25
26	## Pick the right model
27
28	Routes split by video pose-transfer vs image pose-conditioned generation.
29
30	### Video — motion / pose transfer
31
32	Kling 2-6 Motion Control Pro — `kling/kling-2-6/motion-control-pro` (default for video pose transfer)
33	> Takes a reference performance video + a target character image, produces video of the target performing the reference motion / pose.
34	> Pick for: transferring a source video's motion / blocking onto a new character; dance choreography re-shot; sports motion onto a stylized character.
35	> Avoid for: still-image pose conditioning — use Z-Image ControlNet LoRA.
36
37	Kling 2-6 Motion Control Standard — [`kling/kling-2-6/motion-control-standard`](https://www.runcomfy.com/models/kling/kling-2-6/motion-control-standard?utm_source=skills.sh&utm_medium=skill&utm_campaign=controlnet-pose)
38	> Cheaper Kling Motion Control tier.
39	> Pick for: drafts, iteration on motion-control compositions.
40	> Avoid for: final delivery — use Pro.
41
42	Wan 2-2 Animate (video-to-video) — [`community/wan-2-2-animate/video-to-video`](https://www.runcomfy.com/models/community/wan-2-2-animate/video-to-video?utm_source=skills.sh&utm_medium=skill&utm_campaign=controlnet-pose)
43	> Community-published variant on Wan 2-2. Audio-driven character animation that also accepts pose-style conditioning.
44	> Pick for: stylized character animation, mascot work.
45	> Avoid for: photoreal subjects — use Kling Motion Control.
46
47	### Image — pose-conditioned generation
48
49	Z-Image Turbo ControlNet LoRA — [`tongyi-mai/z-image/turbo/controlnet/lora`](https://www.runcomfy.com/models/tongyi-mai/z-image/turbo/controlnet/lora?utm_source=skills.sh&utm_medium=skill&utm_campaign=controlnet-pose)
50	> Z-Image Turbo with a ControlNet LoRA — feed a control image (pose skeleton, depth map, canny) and a prompt, get a generation conditioned on that control.
51	> Pick for: pose-locked image generation, character in specific stance, depth-locked composition.
52	> Avoid for: complex multi-condition stacks (e.g. pose + depth + reference) — those need a ComfyUI workflow.
53
54	---
55
56	## Route 1: Kling Motion Control — video pose transfer
57
58	Model: `kling/kling-2-6/motion-control-pro` (or `/motion-control-standard`)
59	Catalog: [motion-control-pro](https://www.runcomfy.com/models/kling/kling-2-6/motion-control-pro?utm_source=skills.sh&utm_medium=skill&utm_campaign=controlnet-pose) · [`kling` collection](https://www.runcomfy.com/models/collections/kling?utm_source=skills.sh&utm_medium=skill&utm_campaign=controlnet-pose)
60
61	### Invoke
62
63	```bash
64	runcomfy run kling/kling-2-6/motion-control-pro \
65	--input '{
66	"reference_video_url": "https://your-cdn.example/source-performance.mp4",
67	"character_image_url": "https://your-cdn.example/target-character.png"
68	}' \
69	--output-dir ./out
70	```
71
72	### Tips
73
74	- Reference video provides the motion / blocking / camera; character image provides the

People who liked this also viewed

6 picks

Type

controlnet-pose

31stars9forks

View on GitHub

How to install controlnet-pose?

prime-skills/runcomfy-agent-skills/controlnet-pose

$npx -y skills add prime-skills/runcomfy-agent-skills --skill controlnet-pose

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# ControlNet & Pose
2
3	Condition image or video generation on a pose, skeleton, or motion reference. This skill routes across the pose-driven Model API endpoints reachable today and points the agent at ComfyUI workflows for richer ControlNet rigs.
4
5	[runcomfy.com](https://www.runcomfy.com/?utm_source=skills.sh&utm_medium=skill&utm_campaign=controlnet-pose) · [Kling motion control](https://www.runcomfy.com/models/kling/kling-2-6/motion-control-pro?utm_source=skills.sh&utm_medium=skill&utm_campaign=controlnet-pose) · [CLI docs](https://docs.runcomfy.com/cli/introduction?utm_source=skills.sh&utm_medium=skill&utm_campaign=controlnet-pose)
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. Pose-conditioned generate
17	runcomfy run <vendor>/<model> \
18	--input '{"reference_video_url": "...", "character_image_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	---
25
26	## Pick the right model
27
28	Routes split by video pose-transfer vs image pose-conditioned generation.
29
30	### Video — motion / pose transfer
31
32	Kling 2-6 Motion Control Pro — `kling/kling-2-6/motion-control-pro` (default for video pose transfer)
33	> Takes a reference performance video + a target character image, produces video of the target performing the reference motion / pose.
34	> Pick for: transferring a source video's motion / blocking onto a new character; dance choreography re-shot; sports motion onto a stylized character.
35	> Avoid for: still-image pose conditioning — use Z-Image ControlNet LoRA.
36
37	Kling 2-6 Motion Control Standard — [`kling/kling-2-6/motion-control-standard`](https://www.runcomfy.com/models/kling/kling-2-6/motion-control-standard?utm_source=skills.sh&utm_medium=skill&utm_campaign=controlnet-pose)
38	> Cheaper Kling Motion Control tier.
39	> Pick for: drafts, iteration on motion-control compositions.
40	> Avoid for: final delivery — use Pro.
41
42	Wan 2-2 Animate (video-to-video) — [`community/wan-2-2-animate/video-to-video`](https://www.runcomfy.com/models/community/wan-2-2-animate/video-to-video?utm_source=skills.sh&utm_medium=skill&utm_campaign=controlnet-pose)
43	> Community-published variant on Wan 2-2. Audio-driven character animation that also accepts pose-style conditioning.
44	> Pick for: stylized character animation, mascot work.
45	> Avoid for: photoreal subjects — use Kling Motion Control.
46
47	### Image — pose-conditioned generation
48
49	Z-Image Turbo ControlNet LoRA — [`tongyi-mai/z-image/turbo/controlnet/lora`](https://www.runcomfy.com/models/tongyi-mai/z-image/turbo/controlnet/lora?utm_source=skills.sh&utm_medium=skill&utm_campaign=controlnet-pose)
50	> Z-Image Turbo with a ControlNet LoRA — feed a control image (pose skeleton, depth map, canny) and a prompt, get a generation conditioned on that control.
51	> Pick for: pose-locked image generation, character in specific stance, depth-locked composition.
52	> Avoid for: complex multi-condition stacks (e.g. pose + depth + reference) — those need a ComfyUI workflow.
53
54	---
55
56	## Route 1: Kling Motion Control — video pose transfer
57
58	Model: `kling/kling-2-6/motion-control-pro` (or `/motion-control-standard`)
59	Catalog: [motion-control-pro](https://www.runcomfy.com/models/kling/kling-2-6/motion-control-pro?utm_source=skills.sh&utm_medium=skill&utm_campaign=controlnet-pose) · [`kling` collection](https://www.runcomfy.com/models/collections/kling?utm_source=skills.sh&utm_medium=skill&utm_campaign=controlnet-pose)
60
61	### Invoke
62
63	```bash
64	runcomfy run kling/kling-2-6/motion-control-pro \
65	--input '{
66	"reference_video_url": "https://your-cdn.example/source-performance.mp4",
67	"character_image_url": "https://your-cdn.example/target-character.png"
68	}' \
69	--output-dir ./out
70	```
71
72	### Tips
73
74	- Reference video provides the motion / blocking / camera; character image provides the

People who liked this also viewed

6 picks

Type