nano-banana-pro-openrouter

Name: nano-banana-pro-openrouter
Author: github

9.8kinstalls4.6kforks

How to install nano-banana-pro-openrouter?

github/awesome-copilot/nano-banana-pro-openrouter

$npx -y skills add github/awesome-copilot --skill nano-banana-pro-openrouter

Installs into the current project.

Summary

Generate or edit images via OpenRouter with the Gemini 3 Pro Image model. Use for prompt-only image generation, image edits, and multi-image compositing; supports 1K/2K/4K output.

Files · 1

View on GitHub

SKILL.md

1	# Nano Banana Pro OpenRouter
2
3	## Overview
4
5	Generate or edit images with OpenRouter using the `google/gemini-3-pro-image-preview` model. Support prompt-only generation, single-image edits, and multi-image composition.
6
7	### Prompt-only generation
8
9	```
10	uv run {baseDir}/scripts/generate_image.py \
11	--prompt "A cinematic sunset over snow-capped mountains" \
12	--filename sunset.png
13	```
14
15	### Edit a single image
16
17	```
18	uv run {baseDir}/scripts/generate_image.py \
19	--prompt "Replace the sky with a dramatic aurora" \
20	--input-image input.jpg \
21	--filename aurora.png
22	```
23
24	### Compose multiple images
25
26	```
27	uv run {baseDir}/scripts/generate_image.py \
28	--prompt "Combine the subjects into a single studio portrait" \
29	--input-image face1.jpg \
30	--input-image face2.jpg \
31	--filename composite.png
32	```
33
34	## Resolution
35
36	- Use `--resolution` with `1K`, `2K`, or `4K`.
37	- Default is `1K` if not specified.
38
39	## System prompt customization
40
41	The skill reads an optional system prompt from `assets/SYSTEM_TEMPLATE`. This allows you to customize the image generation behavior without modifying code.
42
43	## Behavior and constraints
44
45	- Accept up to 3 input images via repeated `--input-image`.
46	- `--filename` accepts relative paths (saves to current directory) or absolute paths.
47	- If multiple images are returned, append `-1`, `-2`, etc. to the filename.
48	- Print `MEDIA: <path>` for each saved image. Do not read images back into the response.
49
50	## Troubleshooting
51
52	If the script exits non-zero, check stderr against these common blockers:
53
54	\| Symptom \| Resolution \|
55	\|---------\|------------\|
56	\| `OPENROUTER_API_KEY is not set` \| Ask the user to set it. PowerShell: `$env:OPENROUTER_API_KEY = "sk-or-..."` / bash: `export OPENROUTER_API_KEY="sk-or-..."` \|
57	\| `uv: command not found` or not recognized \| macOS/Linux: <code>curl -LsSf https://astral.sh/uv/install.sh \| sh</code>. Windows: <code>powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 \| iex"</code>. Then restart the terminal. \|
58	\| `AuthenticationError` / HTTP 401 \| Key is invalid or has no credits. Verify at <https://openrouter.ai/settings/keys>. \|
59
60	For transient errors (HTTP 429, network timeouts), retry once after 30 seconds. Do not retry the same error more than twice — surface the issue to the user instead.

People who liked this also viewed

6 picks

Type

nano-banana-pro-openrouter

9.8kinstalls4.6kforks

View on GitHub

How to install nano-banana-pro-openrouter?

github/awesome-copilot/nano-banana-pro-openrouter

$npx -y skills add github/awesome-copilot --skill nano-banana-pro-openrouter

Installs into the current project.

Summary

Generate or edit images via OpenRouter with the Gemini 3 Pro Image model. Use for prompt-only image generation, image edits, and multi-image compositing; supports 1K/2K/4K output.

Files · 1

View on GitHub

SKILL.md

1	# Nano Banana Pro OpenRouter
2
3	## Overview
4
5	Generate or edit images with OpenRouter using the `google/gemini-3-pro-image-preview` model. Support prompt-only generation, single-image edits, and multi-image composition.
6
7	### Prompt-only generation
8
9	```
10	uv run {baseDir}/scripts/generate_image.py \
11	--prompt "A cinematic sunset over snow-capped mountains" \
12	--filename sunset.png
13	```
14
15	### Edit a single image
16
17	```
18	uv run {baseDir}/scripts/generate_image.py \
19	--prompt "Replace the sky with a dramatic aurora" \
20	--input-image input.jpg \
21	--filename aurora.png
22	```
23
24	### Compose multiple images
25
26	```
27	uv run {baseDir}/scripts/generate_image.py \
28	--prompt "Combine the subjects into a single studio portrait" \
29	--input-image face1.jpg \
30	--input-image face2.jpg \
31	--filename composite.png
32	```
33
34	## Resolution
35
36	- Use `--resolution` with `1K`, `2K`, or `4K`.
37	- Default is `1K` if not specified.
38
39	## System prompt customization
40
41	The skill reads an optional system prompt from `assets/SYSTEM_TEMPLATE`. This allows you to customize the image generation behavior without modifying code.
42
43	## Behavior and constraints
44
45	- Accept up to 3 input images via repeated `--input-image`.
46	- `--filename` accepts relative paths (saves to current directory) or absolute paths.
47	- If multiple images are returned, append `-1`, `-2`, etc. to the filename.
48	- Print `MEDIA: <path>` for each saved image. Do not read images back into the response.
49
50	## Troubleshooting
51
52	If the script exits non-zero, check stderr against these common blockers:
53
54	\| Symptom \| Resolution \|
55	\|---------\|------------\|
56	\| `OPENROUTER_API_KEY is not set` \| Ask the user to set it. PowerShell: `$env:OPENROUTER_API_KEY = "sk-or-..."` / bash: `export OPENROUTER_API_KEY="sk-or-..."` \|
57	\| `uv: command not found` or not recognized \| macOS/Linux: <code>curl -LsSf https://astral.sh/uv/install.sh \| sh</code>. Windows: <code>powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 \| iex"</code>. Then restart the terminal. \|
58	\| `AuthenticationError` / HTTP 401 \| Key is invalid or has no credits. Verify at <https://openrouter.ai/settings/keys>. \|
59
60	For transient errors (HTTP 429, network timeouts), retry once after 30 seconds. Do not retry the same error more than twice — surface the issue to the user instead.

People who liked this also viewed

6 picks

Type