Install
$ agentstack add skill-supreme-ultimate-novel-to-script-team-image-generation-skill ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ● Environment & secrets Used
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
image-generation-skill
概述
调用 nano banana API 将服化道/分镜提示词转化为图片。支持两种模式:
- 纯文本生图:提示词 → API → PNG 图片
- 参考图生图:提示词 + 本地参考图(base64 编码)→ API → PNG 图片
前置条件
.env或环境变量中配置了NANO_BANANA_API_KEY和NANO_BANANA_BASE_URL- Python 3 已安装
requests库已安装(pip install requests)
输入
- 提示词文件:
outputs/{剧本名}/assets/character-prompts.md、scene-prompts.md或prop-prompts.md - 单条提示词:直接传入文本
- 可选参考图:本地图片路径
输出
- 角色图:
outputs/{剧本名}/images/characters/{前缀}-{序号}.png - 场景图:
outputs/{剧本名}/images/scenes/{前缀}-{序号}.png - 物品图:
outputs/{剧本名}/images/props/{前缀}-{序号}.png
执行流程
步骤1:环境检查
确认 .env 中有 NANO_BANANA_API_KEY 和 NANO_BANANA_BASE_URL:
test -f .env && grep -q "NANO_BANANA_API_KEY" .env && grep -q "NANO_BANANA_BASE_URL" .env
步骤2:生成角色图(第一批,无外部依赖)
python scripts/generate_image.py \
--prompt-file "outputs/{剧本名}/assets/character-prompts.md" \
--output-dir "outputs/{剧本名}/images/characters" \
--prefix char
步骤3:生成物品图(第二批,白底独立策略,仅同族物品间有依赖)
python scripts/generate_image.py \
--prompt-file "outputs/{剧本名}/assets/prop-prompts.md" \
--output-dir "outputs/{剧本名}/images/props" \
--image-base-dir "outputs/{剧本名}/images" \
--prefix prop
步骤4:生成场景图(第三批,依赖角色图和物品图,通过 --image-base-dir 跨文件引用)
python scripts/generate_image.py \
--prompt-file "outputs/{剧本名}/assets/scene-prompts.md" \
--output-dir "outputs/{剧本名}/images/scenes" \
--image-base-dir "outputs/{剧本名}/images" \
--prefix scene
生成顺序很重要:角色 → 物品 → 场景 → 帧图,确保被引用的图先生成。场景引用角色图和物品图,所以必须在场景之前生成。帧图依赖角色图和场景图,所以最后生成。
步骤5:生成帧图(第四批,按集组织,依赖角色图 + 场景图)
帧图由 seedance-storyboard-skill 在生成提示词时同步输出到 03-frame-requests.md。帧图按集组织,不跨集累积。
python scripts/generate_image.py \
--prompt-file "outputs/{剧本名}/storyboard/ep/03-frame-requests.md" \
--output-dir "outputs/{剧本名}/images/frames/ep" \
--image-base-dir "outputs/{剧本名}/images" \
--prefix frame
帧图类型说明:
- 首帧图:用于 I2V-首帧模式,锁定开场构图
- 尾帧图:用于首尾帧模式,锁定结束画面
- 分镜参考图:用于多参考模式多时段,引导各时段画面
步骤6(可选):参考图生图
python scripts/generate_image.py \
--prompt "根据参考图风格生成..." \
--reference-image /path/to/reference.png \
--output-dir "outputs/{剧本名}/images/characters" \
--prefix char-ref
步骤7:检查输出
- 确认图片文件存在且非空
- 报告生成成功/失败的数量
成功标准
- [ ] 所有提示词都已处理
- [ ] 图片文件存在且大小 > 0
- [ ] 文件命名符合
{prefix}-{序号}.png规范 - [ ] 无 API 调用错误
错误处理
- API key 缺失:提示用户配置
.env - API 调用失败:记录错误,继续处理下一条
- 图片解码失败:记录错误,跳过该条
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Supreme-Ultimate
- Source: Supreme-Ultimate/novel-to-script-team
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.