videoagent-image-studio

Name: videoagent-image-studio
Author: pexoai

752stars37forks

How to install videoagent-image-studio?

pexoai/pexo-skills/videoagent-image-studio

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

Installs into the current project.

Summary

Tired of juggling 8 API keys? This skill gives you one-command access to Midjourney, Flux, Ideogram, and more, with zero setup. Use when you want to generate any image without worrying about API keys.

Files · 1

View on GitHub

SKILL.md

1	# 🎨 VideoAgent Image Studio
2
3	Use when: User asks to generate, draw, create, or make any kind of image, photo, illustration, icon, logo, or artwork.
4
5	Generate images with 8 state-of-the-art AI models. This skill automatically picks the best model for the job and handles all the complexity — including Midjourney's async polling — so you can focus on the conversation.
6
7	---
8
9	## Quick Reference
10
11	\| User Intent \| Model \| Speed \|
12	\|---\|---\|---\|
13	\| Artistic, cinematic, painterly \| `midjourney` \| ~15s \|
14	\| Photorealistic, portrait, product \| `flux-pro` \| ~8s \|
15	\| General purpose, balanced \| `flux-dev` \| ~10s \|
16	\| Quick draft, fast iteration \| `flux-schnell` \| ~2s \|
17	\| Image with text, logo, poster \| `ideogram` \| ~10s \|
18	\| Vector art, icon, flat design \| `recraft` \| ~8s \|
19	\| Anime, stylized illustration \| `sdxl` \| ~5s \|
20	\| Gemini-powered, consistent style \| `nano-banana` \| ~12s \|
21
22	---
23
24	## How to Generate an Image
25
26	### Step 1 — Enhance the prompt
27
28	Before calling the script, expand the user's prompt with style, lighting, and quality descriptors appropriate for the chosen model.
29
30	- Midjourney: Add `cinematic lighting`, `ultra detailed`, `--v 7`, `--style raw`
31	- Flux: Add `masterpiece`, `highly detailed`, `sharp focus`, `professional photography`
32	- Ideogram: Be explicit about text content, font style, and layout
33	- Recraft: Specify `vector illustration`, `flat design`, `icon style`
34
35	### Step 2 — Run the script
36
37	```bash
38	node {baseDir}/tools/generate.js \
39	--model <model_id> \
40	--prompt "<enhanced prompt>" \
41	--aspect-ratio <ratio>
42	```
43
44	All parameters:
45
46	\| Parameter \| Default \| Description \|
47	\|---\|---\|---\|
48	\| `--model` \| `flux-dev` \| Model ID from the table above \|
49	\| `--prompt` \| (required) \| The image generation prompt \|
50	\| `--aspect-ratio` \| `1:1` \| `1:1`, `16:9`, `9:16`, `4:3`, `3:4`, `3:2`, `21:9` \|
51	\| `--num-images` \| `1` \| Number of images (1–4; Midjourney always returns 4) \|
52	\| `--negative-prompt` \| — \| Things to avoid (not supported by Midjourney) \|
53	\| `--seed` \| — \| Seed for reproducibility \|
54
55	### Step 3 — Return the result
56
57	The script always waits and returns the final image URL(s). No polling required.
58
59	```json
60	{
61	"success": true,
62	"model": "flux-pro",
63	"imageUrl": "https://...",
64	"images": ["https://..."]
65	}
66	```
67
68	Send the `imageUrl` to the user.
69
70	---
71
72	## Midjourney Actions
73
74	After generating a 4-image grid with Midjourney, offer the user these options:
75
76	```bash
77	# Upscale image #2 (subtle, preserves details)
78	node {baseDir}/tools/generate.js \
79	--model midjourney \
80	--action upscale \
81	--index 2 \
82	--job-id <job_id>
83
84	# Create a strong variation of image #3
85	node {baseDir}/tools/generate.js \
86	--model midjourney \
87	--action variation \
88	--index 3 \
89	--job-id <job_id> \
90	--variation-type 1
91
92	# Regenerate with same prompt
93	node {baseDir}/tools/generate.js \
94	--model midjourney \
95	--action reroll \
96	--job-id <job_id>
97	```
98
99	Upscale types: `0` = Subtle (default, best for photos), `1` = Creative (best for illustrations)
100
101	Variation types: `0` = Subtle (default), `1` = Strong (dramatic changes)
102
103	---
104
105	## Example Conversations
106
107	User: "Draw a snow leopard on a snowy mountain with cinematic lighting"
108
109	```bash
110	# Choose midjourney for artistic quality
111	node {baseDir}/tools/generate.js \
112	--model midjourney \
113	--prompt "a majestic snow leopard on a snowy mountain peak, cinematic lighting, dramatic atmosphere, ultra detailed --ar 16:9 --v 7" \
114	--aspect-ratio 16:9
115	```
116
117	> 🎨 Done! Which one to upscale? (U1-U4) Or create a variant? (V1-V4)
118
119	---
120
121	User: "Use Flux to generate a perfume product poster, white background"
122
123	```bash
124	# Choose flux-pro for photorealistic product shots
125	node {baseDir}/tools/generate.js \
126	--model flux-pro \
127	--prompt "a luxury perfume bottle on a clean white background, professional product photography, soft shadows, 8k, highly detailed" \
128	--aspect-ratio 3:4
129	```
130
131	---
132
133	User: "Show me a quick draft"
134
135	```bash
136	# flux-schnell for instant previews
137	node {baseDir}/tools/generate.js \
138	--model flux-schnell \
139	--prompt "..." \
140	--aspect-ratio 1:1
141	```
142
143	---
144
145	User: "Make me an App icon, flat style, blue theme"
146
147	```bash
148	# recraft for vector/icon style
149	node {baseDir}/tools/generate.js \
150	--model recraft \
151	--prompt "a minimal flat design app icon, blue color scheme, simple geometric shapes, vector style, white background"
152	```
153
154	---
155
156	## Setup
157
158	**Zero API k

People who liked this also viewed

6 picks

Type

videoagent-image-studio

752stars37forks

View on GitHub

How to install videoagent-image-studio?

pexoai/pexo-skills/videoagent-image-studio

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# 🎨 VideoAgent Image Studio
2
3	Use when: User asks to generate, draw, create, or make any kind of image, photo, illustration, icon, logo, or artwork.
4
5	Generate images with 8 state-of-the-art AI models. This skill automatically picks the best model for the job and handles all the complexity — including Midjourney's async polling — so you can focus on the conversation.
6
7	---
8
9	## Quick Reference
10
11	\| User Intent \| Model \| Speed \|
12	\|---\|---\|---\|
13	\| Artistic, cinematic, painterly \| `midjourney` \| ~15s \|
14	\| Photorealistic, portrait, product \| `flux-pro` \| ~8s \|
15	\| General purpose, balanced \| `flux-dev` \| ~10s \|
16	\| Quick draft, fast iteration \| `flux-schnell` \| ~2s \|
17	\| Image with text, logo, poster \| `ideogram` \| ~10s \|
18	\| Vector art, icon, flat design \| `recraft` \| ~8s \|
19	\| Anime, stylized illustration \| `sdxl` \| ~5s \|
20	\| Gemini-powered, consistent style \| `nano-banana` \| ~12s \|
21
22	---
23
24	## How to Generate an Image
25
26	### Step 1 — Enhance the prompt
27
28	Before calling the script, expand the user's prompt with style, lighting, and quality descriptors appropriate for the chosen model.
29
30	- Midjourney: Add `cinematic lighting`, `ultra detailed`, `--v 7`, `--style raw`
31	- Flux: Add `masterpiece`, `highly detailed`, `sharp focus`, `professional photography`
32	- Ideogram: Be explicit about text content, font style, and layout
33	- Recraft: Specify `vector illustration`, `flat design`, `icon style`
34
35	### Step 2 — Run the script
36
37	```bash
38	node {baseDir}/tools/generate.js \
39	--model <model_id> \
40	--prompt "<enhanced prompt>" \
41	--aspect-ratio <ratio>
42	```
43
44	All parameters:
45
46	\| Parameter \| Default \| Description \|
47	\|---\|---\|---\|
48	\| `--model` \| `flux-dev` \| Model ID from the table above \|
49	\| `--prompt` \| (required) \| The image generation prompt \|
50	\| `--aspect-ratio` \| `1:1` \| `1:1`, `16:9`, `9:16`, `4:3`, `3:4`, `3:2`, `21:9` \|
51	\| `--num-images` \| `1` \| Number of images (1–4; Midjourney always returns 4) \|
52	\| `--negative-prompt` \| — \| Things to avoid (not supported by Midjourney) \|
53	\| `--seed` \| — \| Seed for reproducibility \|
54
55	### Step 3 — Return the result
56
57	The script always waits and returns the final image URL(s). No polling required.
58
59	```json
60	{
61	"success": true,
62	"model": "flux-pro",
63	"imageUrl": "https://...",
64	"images": ["https://..."]
65	}
66	```
67
68	Send the `imageUrl` to the user.
69
70	---
71
72	## Midjourney Actions
73
74	After generating a 4-image grid with Midjourney, offer the user these options:
75
76	```bash
77	# Upscale image #2 (subtle, preserves details)
78	node {baseDir}/tools/generate.js \
79	--model midjourney \
80	--action upscale \
81	--index 2 \
82	--job-id <job_id>
83
84	# Create a strong variation of image #3
85	node {baseDir}/tools/generate.js \
86	--model midjourney \
87	--action variation \
88	--index 3 \
89	--job-id <job_id> \
90	--variation-type 1
91
92	# Regenerate with same prompt
93	node {baseDir}/tools/generate.js \
94	--model midjourney \
95	--action reroll \
96	--job-id <job_id>
97	```
98
99	Upscale types: `0` = Subtle (default, best for photos), `1` = Creative (best for illustrations)
100
101	Variation types: `0` = Subtle (default), `1` = Strong (dramatic changes)
102
103	---
104
105	## Example Conversations
106
107	User: "Draw a snow leopard on a snowy mountain with cinematic lighting"
108
109	```bash
110	# Choose midjourney for artistic quality
111	node {baseDir}/tools/generate.js \
112	--model midjourney \
113	--prompt "a majestic snow leopard on a snowy mountain peak, cinematic lighting, dramatic atmosphere, ultra detailed --ar 16:9 --v 7" \
114	--aspect-ratio 16:9
115	```
116
117	> 🎨 Done! Which one to upscale? (U1-U4) Or create a variant? (V1-V4)
118
119	---
120
121	User: "Use Flux to generate a perfume product poster, white background"
122
123	```bash
124	# Choose flux-pro for photorealistic product shots
125	node {baseDir}/tools/generate.js \
126	--model flux-pro \
127	--prompt "a luxury perfume bottle on a clean white background, professional product photography, soft shadows, 8k, highly detailed" \
128	--aspect-ratio 3:4
129	```
130
131	---
132
133	User: "Show me a quick draft"
134
135	```bash
136	# flux-schnell for instant previews
137	node {baseDir}/tools/generate.js \
138	--model flux-schnell \
139	--prompt "..." \
140	--aspect-ratio 1:1
141	```
142
143	---
144
145	User: "Make me an App icon, flat style, blue theme"
146
147	```bash
148	# recraft for vector/icon style
149	node {baseDir}/tools/generate.js \
150	--model recraft \
151	--prompt "a minimal flat design app icon, blue color scheme, simple geometric shapes, vector style, white background"
152	```
153
154	---
155
156	## Setup
157
158	**Zero API k

People who liked this also viewed

6 picks

Type