Qwen Comic Gen

Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image). Use for image create/modify requests incl. edits. Supports text-to-image + image-to-image; 1K...

copies: implexa run clawhub/qwen-comic-gen

view source

installs

stars

karma

SkillRank score ↗

7.4/ 10

evaluated by implexa, claude-haiku-4-5 · 2026-05-26

qwen-comic-gen wraps gemini 3 pro image to handle text-to-image and image-to-image workflows at 1k/2k/4k resolutions. covers generation, editing, iteration patterns, and api key resolution with concrete command examples.

structure

8.0

trigger phrases

6.0

procedure

8.0

edge cases

7.0

documentation

7.0

strengths

view original SKILL.md from clawhubclick to expand

---
name: nano-banana-pro
description: Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image). Use for image create/modify requests incl. edits. Supports text-to-image + image-to-image; 1K/2K/4K; use --input-image.
---

# Nano Banana Pro Image Generation & Editing

Generate new images or edit existing ones using Google's Nano Banana Pro API (Gemini 3 Pro Image).

## Usage

Run the script using absolute path (do NOT cd to skill directory first):

**Generate new image:**
```bash
uv run ~/.codex/skills/nano-banana-pro/scripts/generate_image.py --prompt "your image description" --filename "output-name.png" [--resolution 1K|2K|4K] [--api-key KEY]
```

**Edit existing image:**
```bash
uv run ~/.codex/skills/nano-banana-pro/scripts/generate_image.py --prompt "editing instructions" --filename "output-name.png" --input-image "path/to/input.png" [--resolution 1K|2K|4K] [--api-key KEY]
```

**Important:** Always run from the user's current working directory so images are saved where the user is working, not in the skill directory.

## Default Workflow (draft → iterate → final)

Goal: fast iteration without burning time on 4K until the prompt is correct.

- Draft (1K): quick feedback loop
  - `uv run ~/.codex/skills/nano-banana-pro/scripts/generate_image.py --prompt "<draft prompt>" --filename "yyyy-mm-dd-hh-mm-ss-draft.png" --resolution 1K`
- Iterate: adjust prompt in small diffs; keep filename new per run
  - If editing: keep the same `--input-image` for every iteration until you’re happy.
- Final (4K): only when prompt is locked
  - `uv run ~/.codex/skills/nano-banana-pro/scripts/generate_image.py --prompt "<final prompt>" --filename "yyyy-mm-dd-hh-mm-ss-final.png" --resolution 4K`

## Resolution Options

The Gemini 3 Pro Image API supports three resolutions (uppercase K required):

- **1K** (default) - ~1024px resolution
- **2K** - ~2048px resolution
- **4K** - ~4096px resolution

Map user requests to API parameters:
- No mention of resolution → `1K`
- "low resolution", "1080", "1080p", "1K" → `1K`
- "2K", "2048", "normal", "medium resolution" → `2K`
- "high resolution", "high-res", "hi-res", "4K", "ultra" → `4K`

## API Key

The script checks for API key in this order:
1. `--api-key` argument (use if user provided key in chat)
2. `GEMINI_API_KEY` environment variable

If neither is available, the script exits with an error message.

## Preflight + Common Failures (fast fixes)

- Preflight:
  - `command -v uv` (must exist)
  - `test -n \"$GEMINI_API_KEY\"` (or pass `--api-key`)
  - If editing: `test -f \"path/to/input.png\"`

- Common failures:
  - `Error: No API key provided.` → set `GEMINI_API_KEY` or pass `--api-key`
  - `Error loading input image:` → wrong path / unreadable file; verify `--input-image` points to a real image
  - “quota/permission/403” style API errors → wrong key, no access, or quota exceeded; try a different key/account

## Filename Generation

Generate filenames with the pattern: `yyyy-mm-dd-hh-mm-ss-name.png`

**Format:** `{timestamp}-{descriptive-name}.png`
- Timestamp: Current date/time in format `yyyy-mm-dd-hh-mm-ss` (24-hour format)
- Name: Descriptive lowercase text with hyphens
- Keep the descriptive part concise (1-5 words typically)
- Use context from user's prompt or conversation
- If unclear, use random identifier (e.g., `x9k2`, `a7b3`)

Examples:
- Prompt "A serene Japanese garden" → `2025-11-23-14-23-05-japanese-garden.png`
- Prompt "sunset over mountains" → `2025-11-23-15-30-12-sunset-mountains.png`
- Prompt "create an image of a robot" → `2025-11-23-16-45-33-robot.png`
- Unclear context → `2025-11-23-17-12-48-x9k2.png`

## Image Editing

When the user wants to modify an existing image:
1. Check if they provide an image path or reference an image in the current directory
2. Use `--input-image` parameter with the path to the image
3. The prompt should contain editing instructions (e.g., "make the sky more dramatic", "remove the person", "change to cartoon style")
4. Common editing tasks: add/remove elements, change style, adjust colors, blur background, etc.

## Prompt Handling

**For generation:** Pass user's image description as-is to `--prompt`. Only rework if clearly insufficient.

**For editing:** Pass editing instructions in `--prompt` (e.g., "add a rainbow in the sky", "make it look like a watercolor painting")

Preserve user's creative intent in both cases.

## Prompt Templates (high hit-rate)

Use templates when the user is vague or when edits must be precise.

- Generation template:
  - “Create an image of: <subject>. Style: <style>. Composition: <camera/shot>. Lighting: <lighting>. Background: <background>. Color palette: <palette>. Avoid: <list>.”

- Editing template (preserve everything else):
  - “Change ONLY: <single change>. Keep identical: subject, composition/crop, pose, lighting, color palette, background, text, and overall style. Do not add new objects. If text exists, keep it unchanged.”

## Output

- Saves PNG to current directory (or specified path if filename includes directory)
- Script outputs the full path to the generated image
- **Do not read the image back** - just inform the user of the saved path

## Examples

**Generate new image:**
```bash
uv run ~/.codex/skills/nano-banana-pro/scripts/generate_image.py --prompt "A serene Japanese garden with cherry blossoms" --filename "2025-11-23-14-23-05-japanese-garden.png" --resolution 4K
```

**Edit existing image:**
```bash
uv run ~/.codex/skills/nano-banana-pro/scripts/generate_image.py --prompt "make the sky more dramatic with storm clouds" --filename "2025-11-23-14-25-30-dramatic-sky.png" --input-image "original-photo.jpg" --resolution 2K
```

don't have the plugin yet? install it then click "run inline in claude" again.

extracted and formalized intent, inputs (including env var setup and external API connection), decision points (resolution mapping, generation vs editing, api key source, input validation, error cases, network fallback), and output contract with exact file format and dimensions; preserved original procedure and examples faithfully.

Qwen Comic Gen

Item: Qwen Comic Gen
Rating: 7.4
Author: Implexa

Generate new images or edit existing ones using Google's Nano Banana Pro API (Gemini 3 Pro Image). Use this skill for any image creation or modification request, whether text-to-image generation or image-to-image editing. Supports three resolutions (1K, 2K, 4K) and works best with iterative prompting (draft at 1K, final at 4K).

intent

Generate or edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when a user requests image creation from text, image editing/modification, or image generation with specific style/composition requirements. Best for fast iteration: start at 1K resolution for prompt validation, bump to 4K only when the prompt is locked. Supports both text-to-image and image-to-image workflows.

inputs

Required:

Google Gemini API key (from GEMINI_API_KEY env var or --api-key flag)
User prompt (text description for generation or editing instructions for edits)
Output filename (pattern: yyyy-mm-dd-hh-mm-ss-descriptive-name.png)

Conditional:

Input image path (only for image-to-image editing via --input-image)

Environment / Setup:

uv command-line tool must be installed and in PATH
GEMINI_API_KEY env var set, or API key passed as --api-key argument
For edits: input image must exist at specified path and be readable (PNG, JPG, etc.)

External Connection:

Google Gemini 3 Pro Image API (requires valid API key with image generation permissions)

procedure

Preflight checks:
- Verify uv is installed: run command -v uv
- Verify API key is available: check GEMINI_API_KEY env var or plan to pass --api-key flag
- If editing: verify input image exists at the path specified by user; test with test -f "path/to/input.png"
Parse user intent:
- Determine if user wants generation (text-to-image) or editing (image-to-image)
- For generation: capture user's image description as-is
- For editing: capture editing instructions and input image path from user
Map resolution request to API parameter:
- Extract resolution from user request or use default 1K
- Map user language to API parameter (see decision points below)
Generate output filename:
- Create timestamp in format yyyy-mm-dd-hh-mm-ss using current date/time (24-hour)
- Extract descriptive name from user prompt (1-5 lowercase words, hyphen-separated)
- If prompt context is unclear, use random identifier (e.g., x9k2)
- Output filename: {timestamp}-{descriptive-name}.png
Build command:
- Base: uv run ~/.codex/skills/nano-banana-pro/scripts/generate_image.py
- Add --prompt "user prompt or editing instructions"
- Add --filename "generated-filename.png"
- If editing: add --input-image "path/to/input.png"
- Add --resolution 1K|2K|4K (explicit, always include)
- If user provided API key in chat: add --api-key KEY
Execute from user's current working directory:
- Do NOT cd to skill directory first
- Run command with absolute path to script
- Images save to user's current directory (or specified path if filename includes directory prefix)
Capture and report output:
- Script outputs full path to generated image
- Report path to user; do not read/load image back into chat

decision points

For resolution mapping:

User says "1K", "1080", "1080p", "low resolution", or no resolution mentioned: use 1K (default, fast feedback)
User says "2K", "2048", "normal", "medium resolution": use 2K
User says "4K", "ultra", "high resolution", "high-res", "hi-res": use 4K (only when prompt is finalized)

For generation vs. editing:

If user provides input image path or references an existing image: use --input-image parameter; treat as image-to-image
Else: text-to-image generation (no --input-image)

For API key source:

If user provides key in chat: use --api-key KEY flag
Else: script checks GEMINI_API_KEY env var
If neither available: script exits with error (no fallback)

For input image validation (editing only):

If --input-image path does not exist or is unreadable: script fails with "Error loading input image"
User must verify path and re-run; check for typos, permissions, or wrong file type

For quota/auth failures:

If API returns 403/quota error: API key may be invalid, account may lack permissions, or quota exceeded
User must verify API key, try different account, or wait for quota reset

For empty/null results:

If API returns successfully but image is blank/malformed: API call succeeded but content was filtered or generation failed
User should rephrase prompt (avoid restricted terms) and re-run

For network timeouts:

If request hangs or times out: network connectivity issue or API is slow
User should retry with lower resolution (1K) or check internet connection

output contract

File location: PNG saved to user's current working directory (or directory specified in --filename path)
File naming: yyyy-mm-dd-hh-mm-ss-descriptive-name.png (exact timestamp format required, lowercase name, hyphens)
Return value: Script outputs full absolute path to saved image (e.g., /home/user/project/2025-11-23-14-23-05-japanese-garden.png)
Image dimensions: depends on resolution flag
- 1K: ~1024px
- 2K: ~2048px
- 4K: ~4096px
Format: Always PNG, even if input is JPG
Success indicator: File exists at reported path; can be opened/viewed immediately

outcome signal

Script runs without error and outputs: Image saved to: /path/to/filename.png
File exists in user's current directory with the exact filename provided
User can open and view the image in any image viewer
For edits: image shows requested modifications (e.g., sky is more dramatic, style changed, element removed)
For generation: image matches user's original description or intent

Qwen Comic Gen

related skills

Qwen Comic Gen

intent

inputs

procedure

decision points

output contract

outcome signal