videoagent-video-studio

Name: videoagent-video-studio
Author: pexoai

752stars37forks

How to install videoagent-video-studio?

pexoai/pexo-skills/videoagent-video-studio

$npx -y skills add pexoai/pexo-skills --skill videoagent-video-studio

Installs into the current project.

Summary

Generate short AI videos from text or images — text-to-video, image-to-video, and reference-based generation — with zero API key setup. Use when the user wants to create a video clip, animate an image, or generate video from a description.

Files · 1

View on GitHub

SKILL.md

1	# 🎬 VideoAgent Video Studio
2
3	Use when: User asks to generate a video, create a video from text, animate an image, make a short clip, or produce AI video.
4
5	Generate short AI videos with 7 backends. This skill picks the right mode (text-to-video or image-to-video), enhances the prompt for best results, and returns the video URL.
6
7	---
8
9	## Quick Reference
10
11	\| User Intent \| Mode \| Typical Duration \|
12	\|-------------\|------\|------------------\|
13	\| "Make a video of..." (no image) \| `text-to-video` \| 4–10 s \|
14	\| "Animate this image" / "Make this move" \| `image-to-video` \| 4–6 s \|
15	\| "Turn this into a video with..." \| `image-to-video` \| 4–6 s \|
16	\| Cinematic, story, ad \| Prefer `text-to-video` with detailed prompt \| 5–10 s \|
17
18	### Generation Modes
19
20	\| Mode \| Description \| Models \|
21	\|------\|-------------\|--------\|
22	\| text-to-video \| Text prompt only → video \| minimax, kling, veo, hunyuan, grok, seedance \|
23	\| image-to-video \| Single image + prompt → animated clip \| minimax, kling, veo, pixverse, grok, seedance \|
24	\| reference-based \| Reference images/video → consistent output \| minimax, kling, veo, hunyuan, grok, seedance \|
25
26	### Models (use `--model <id>`)
27
28	\| Model ID \| T2V \| I2V \| Reference \| Notes \|
29	\|----------\|-----\|-----\|-----------\|-------\|
30	\| `minimax` \| ✅ \| ✅ \| ✅ \| Subject reference image, character consistency \|
31	\| `kling` \| ✅ \| ✅ \| ✅ \| Multi-element / character / keyframe (O3) \|
32	\| `veo` \| ✅ \| ✅ \| ✅ \| Google Veo 3.1, multiple reference images \|
33	\| `hunyuan` \| ✅ \| — \| ✅ \| Video-to-video style transfer \|
34	\| `pixverse` \| — \| ✅ \| — \| Stylized image-to-video \|
35	\| `grok` \| ✅ \| ✅ \| ✅ \| Video editing via reference video \|
36	\| `seedance` \| ✅ \| ✅ \| ✅ \| Seedance 1.5 Pro, synchronized audio, 4–12 s \|
37
38	Full model details and endpoint reference: [references/models.md](references/models.md).
39
40	---
41
42	## How to Generate a Video
43
44	### Step 1 — Choose mode and enhance the prompt
45
46	- Text-to-video: Expand with subject, action, camera movement, lighting, and style. Be specific about motion (e.g. "camera slowly zooms in", "character walks left to right").
47	- Image-to-video: Describe the motion to apply to the image (e.g. "gentle breeze in the hair", "camera pans across the scene"). See [references/prompt_guide.md](references/prompt_guide.md) for patterns.
48
49	### Step 2 — Run the script
50
51	Text-to-video:
52	```bash
53	node {baseDir}/tools/generate.js \
54	--mode text-to-video \
55	--prompt "<enhanced prompt>" \
56	--duration <seconds> \
57	--aspect-ratio <ratio>
58	```
59
60	Image-to-video:
61	```bash
62	node {baseDir}/tools/generate.js \
63	--mode image-to-video \
64	--prompt "<motion description>" \
65	--image-url "<public image URL>" \
66	--duration <seconds> \
67	--aspect-ratio <ratio>
68	```
69
70	Parameters:
71
72	\| Parameter \| Default \| Description \|
73	\|-----------\|---------\|-------------\|
74	\| `--mode` \| `text-to-video` \| `text-to-video` or `image-to-video` \|
75	\| `--prompt` \| (required) \| Scene or motion description \|
76	\| `--image-url` \| — \| Required for `image-to-video`; public image URL \|
77	\| `--duration` \| `5` \| Length in seconds (typically 4–10) \|
78	\| `--aspect-ratio` \| `16:9` \| `16:9`, `9:16`, `1:1`, `4:3`, `3:4` \|
79	\| `--model` \| `auto` \| Model ID (e.g. `kling`, `veo`, `grok`, `seedance`); `auto` = proxy picks \|
80
81	Other commands:
82
83	\| Command \| Description \|
84	\|---------\|-------------\|
85	\| `node tools/generate.js --list-models` \| List available models from the proxy \|
86	\| `node tools/generate.js --status --job-id <id>` \| Check async job status \|
87
88	### Step 3 — Return the result
89
90	The script returns JSON:
91
92	```json
93	{
94	"success": true,
95	"mode": "text-to-video",
96	"videoUrl": "https://...",
97	"duration": 5,
98	"aspectRatio": "16:9"
99	}
100	```
101
102	Send `videoUrl` to the user.
103
104	---
105
106	## Example Conversations
107
108	User: "Generate a short video of a cat walking in the rain, cinematic."
109
110	```bash
111	node {baseDir}/tools/generate.js \
112	--mode text-to-video \
113	--prompt "A cat walking through rain, wet streets, neon reflections, cinematic lighting, slow motion, 4K" \
114	--duration 5 \
115	--aspect-ratio 16:9
116	```
117
118	---
119
120	User: "Animate this photo" (user uploads a landscape)
121
122	```bash
123	node {baseDir}/tools/generate.js \
124	--mode image-to-video \
125	--prompt "Gentle clouds moving across the sky, subtle grass movement, cinematic atmosphere" \
126	--image-url "https://..." \
127	--duration 5 \
128	--aspect-ratio 16:9
129	```
130
131	---
132
133	User: "Make a 10-second vertical vi

People who liked this also viewed

6 picks

Type

videoagent-video-studio

752stars37forks

View on GitHub

How to install videoagent-video-studio?

pexoai/pexo-skills/videoagent-video-studio

$npx -y skills add pexoai/pexo-skills --skill videoagent-video-studio

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# 🎬 VideoAgent Video Studio
2
3	Use when: User asks to generate a video, create a video from text, animate an image, make a short clip, or produce AI video.
4
5	Generate short AI videos with 7 backends. This skill picks the right mode (text-to-video or image-to-video), enhances the prompt for best results, and returns the video URL.
6
7	---
8
9	## Quick Reference
10
11	\| User Intent \| Mode \| Typical Duration \|
12	\|-------------\|------\|------------------\|
13	\| "Make a video of..." (no image) \| `text-to-video` \| 4–10 s \|
14	\| "Animate this image" / "Make this move" \| `image-to-video` \| 4–6 s \|
15	\| "Turn this into a video with..." \| `image-to-video` \| 4–6 s \|
16	\| Cinematic, story, ad \| Prefer `text-to-video` with detailed prompt \| 5–10 s \|
17
18	### Generation Modes
19
20	\| Mode \| Description \| Models \|
21	\|------\|-------------\|--------\|
22	\| text-to-video \| Text prompt only → video \| minimax, kling, veo, hunyuan, grok, seedance \|
23	\| image-to-video \| Single image + prompt → animated clip \| minimax, kling, veo, pixverse, grok, seedance \|
24	\| reference-based \| Reference images/video → consistent output \| minimax, kling, veo, hunyuan, grok, seedance \|
25
26	### Models (use `--model <id>`)
27
28	\| Model ID \| T2V \| I2V \| Reference \| Notes \|
29	\|----------\|-----\|-----\|-----------\|-------\|
30	\| `minimax` \| ✅ \| ✅ \| ✅ \| Subject reference image, character consistency \|
31	\| `kling` \| ✅ \| ✅ \| ✅ \| Multi-element / character / keyframe (O3) \|
32	\| `veo` \| ✅ \| ✅ \| ✅ \| Google Veo 3.1, multiple reference images \|
33	\| `hunyuan` \| ✅ \| — \| ✅ \| Video-to-video style transfer \|
34	\| `pixverse` \| — \| ✅ \| — \| Stylized image-to-video \|
35	\| `grok` \| ✅ \| ✅ \| ✅ \| Video editing via reference video \|
36	\| `seedance` \| ✅ \| ✅ \| ✅ \| Seedance 1.5 Pro, synchronized audio, 4–12 s \|
37
38	Full model details and endpoint reference: [references/models.md](references/models.md).
39
40	---
41
42	## How to Generate a Video
43
44	### Step 1 — Choose mode and enhance the prompt
45
46	- Text-to-video: Expand with subject, action, camera movement, lighting, and style. Be specific about motion (e.g. "camera slowly zooms in", "character walks left to right").
47	- Image-to-video: Describe the motion to apply to the image (e.g. "gentle breeze in the hair", "camera pans across the scene"). See [references/prompt_guide.md](references/prompt_guide.md) for patterns.
48
49	### Step 2 — Run the script
50
51	Text-to-video:
52	```bash
53	node {baseDir}/tools/generate.js \
54	--mode text-to-video \
55	--prompt "<enhanced prompt>" \
56	--duration <seconds> \
57	--aspect-ratio <ratio>
58	```
59
60	Image-to-video:
61	```bash
62	node {baseDir}/tools/generate.js \
63	--mode image-to-video \
64	--prompt "<motion description>" \
65	--image-url "<public image URL>" \
66	--duration <seconds> \
67	--aspect-ratio <ratio>
68	```
69
70	Parameters:
71
72	\| Parameter \| Default \| Description \|
73	\|-----------\|---------\|-------------\|
74	\| `--mode` \| `text-to-video` \| `text-to-video` or `image-to-video` \|
75	\| `--prompt` \| (required) \| Scene or motion description \|
76	\| `--image-url` \| — \| Required for `image-to-video`; public image URL \|
77	\| `--duration` \| `5` \| Length in seconds (typically 4–10) \|
78	\| `--aspect-ratio` \| `16:9` \| `16:9`, `9:16`, `1:1`, `4:3`, `3:4` \|
79	\| `--model` \| `auto` \| Model ID (e.g. `kling`, `veo`, `grok`, `seedance`); `auto` = proxy picks \|
80
81	Other commands:
82
83	\| Command \| Description \|
84	\|---------\|-------------\|
85	\| `node tools/generate.js --list-models` \| List available models from the proxy \|
86	\| `node tools/generate.js --status --job-id <id>` \| Check async job status \|
87
88	### Step 3 — Return the result
89
90	The script returns JSON:
91
92	```json
93	{
94	"success": true,
95	"mode": "text-to-video",
96	"videoUrl": "https://...",
97	"duration": 5,
98	"aspectRatio": "16:9"
99	}
100	```
101
102	Send `videoUrl` to the user.
103
104	---
105
106	## Example Conversations
107
108	User: "Generate a short video of a cat walking in the rain, cinematic."
109
110	```bash
111	node {baseDir}/tools/generate.js \
112	--mode text-to-video \
113	--prompt "A cat walking through rain, wet streets, neon reflections, cinematic lighting, slow motion, 4K" \
114	--duration 5 \
115	--aspect-ratio 16:9
116	```
117
118	---
119
120	User: "Animate this photo" (user uploads a landscape)
121
122	```bash
123	node {baseDir}/tools/generate.js \
124	--mode image-to-video \
125	--prompt "Gentle clouds moving across the sky, subtle grass movement, cinematic atmosphere" \
126	--image-url "https://..." \
127	--duration 5 \
128	--aspect-ratio 16:9
129	```
130
131	---
132
133	User: "Make a 10-second vertical vi

People who liked this also viewed

6 picks

Type