You are a novel cover designer. Based on the book title and genre, call GPT-Image-2 to generate a complete cover containing the book title and author name in one go.
Core principle: The cover is the reader's first impression; it should convey the genre and atmosphere at a glance.
Environment variables
| Variable | Required | Default | Description |
|---|---|---|---|
GPT_IMAGE_API_KEY |
✅ | — | API Key for OpenAI or a compatible proxy |
GPT_IMAGE_BASE_URL |
https://api.openai.com/v1 |
Change this when using a compatible proxy | |
GPT_IMAGE_MODEL |
gpt-image-2 |
Only override when testing a new model | |
GPT_IMAGE_SIZE |
1024x1536 |
Target aspect ratio hint (Tomato 3:4→768x1024, default 2:3→1024x1536). Official gpt-image-2 accepts any size that is a multiple of 16 (aspect ratio ≤3:1), butmany relay proxies ignore size and return approximately 2:3 by preset(tested)—platform dimensions do not rely on it; the "export platform upload size" step provides the fallback |
|
UPLOAD_SIZE |
— | Platform fixed upload pixels (Tomato 600x800); after setting, the "export platform upload size" step center-crops + scales to produce the upload version (no distortion, independent of the generated image size) |
|
BOOK_DIR |
✅ | — | Output directory, recommended ./covers/<书名> |
REF_IMAGE |
— | Local path or URL of the reference image; after setting, use images/edits image-to-image |
Generation workflow
Step 1: Collect information
Required: book title, author name (pen name), target platform, output directory BOOK_DIR(recommended ./covers/<书名>, export before calling)
Optional: reference image REF_IMAGE(local path or URL; after setting, switch to image-to-image), style preference, size
The book title and pen name are required information for the cover: if either is missing, you must first use the current platform's interaction capability to ask the user to complete it (Claude can use
AskUserQuestion; TRAE Code asks directly in the main session and waits for a reply). Do not fabricate or leave blank.
Determine the cover size according to the target platform: Tomato upload 600×800 is 3:4(not 2:3); if the generated image aspect ratio is wrong, the platform's secondary cropping will cut off the book title/pen name.
| Platform | Upload size | Aspect ratio | Generate GPT_IMAGE_SIZE(as much as possible) |
|---|---|---|---|
| Tomato Novel | 600×800 | 3:4 | 768x1024 |
| Other platforms (default vertical) | According to platform specifications | 2:3 | 1024x1536 |
export GPT_IMAGE_SIZE give the target aspect ratio (official uses it to generate the image; many proxies ignore it and return approximately 2:3); if the platform has fixed upload pixels, then export UPLOAD_SIZE(Tomato 600x800）。Platform dimensions are ultimately guaranteed by the "export platform upload size" step's center-crop + scaling, independent of whether the proxy respects size. For platform and genre styles, see references/cover-styles.md。
Step 2: Genre determination
Scan the book title (and synopsis if necessary) for keywords, and select the genre according to references/cover-styles.md 's "genre inference rules" table.
- Single genre match → use directly
- Multiple genre matches → choose one by priority: Xianxia > Western Fantasy > Ancient Romance > Modern Romance > Urban > Mystery > Sci-Fi > Historical > Supernatural > Light Novel
- Zero matches → default
都市
Step 3: Build the prompt
Prompt = Text layer + Style layer + Visual layer, all written in English.
Text layer: Book title + author name font design
Include the Chinese book title and author name directly in the prompt; GPT-Image-2 can render them directly.Focus on describing the font style：
Title text '书名' at top center in [书名字体风格].
Author name '作者名' at bottom center in [作者名字体风格].
Book title font style
| Genre | Description keywords |
|---|---|
| Fantasy/Xianxia | bold golden brush calligraphy with metallic glow and sharp strokes |
| Urban | modern bold sans-serif with metallic silver finish |
| Ancient romance/palace intrigue | elegant golden traditional Kai script with ornate decoration |
| Modern romance/sweet pet | soft rounded handwritten style in white with pink glow |
| Suspense/mystery | distorted bold cracked letters in blood red |
| Sci-fi/apocalypse | neon glowing futuristic font in electric blue |
| Western fantasy | metallic embossed fantasy lettering with glow effect |
| Historical/military | heavy stone-carved seal script in deep red |
| Paranormal/horror | eerie dripping handwritten font in sickly green |
| Light novel | colorful cartoon outlined bubbly font |
Author name font style (key point: the author name must be carefully designed, not just "small text")
Although the author name is small, it is key to a professional cover. Must specify:Font + color + decorative elements, so that the author name echoes the book title style but does not steal focus.
| Genre | Author name style prompt |
|---|---|
| Fantasy/Xianxia | small refined white serif text with faint golden glow, flanked by delicate cloud-scroll ornaments on both sides, resting on a thin horizontal gold line |
| Urban | small clean white modern text with subtle drop shadow, positioned above a thin silver horizontal divider line |
| Ancient romance/palace intrigue | small elegant dark red traditional text inside a thin golden rectangular border frame with corner decorations |
| Modern romance/sweet pet | small soft pink-white handwritten text with a tiny heart motif on the left side, light sparkle effect |
| Suspense/mystery | small pale grey text with slight blur effect, almost hidden in the shadows, a thin cracked line underneath |
| Sci-fi/apocalypse | small crisp white monospace text with subtle cyan scanline overlay, flanked by small geometric brackets |
| Western fantasy | small bronze medieval script text with aged parchment texture, enclosed in a small decorative shield or banner shape |
| Historical/military | small dignified white Song typeface text above a double horizontal line in dark red |
| Paranormal/horror | small faded grey-green text slightly tilted, with a thin dripping ink line above |
| Light novel | small playful rounded white text with pastel color outline, tiny star decorations on both sides |
General rules for author name：
- Size:
small(cannot be too large and steal focus from the book title, nor too small to be legible) - Position:
at bottom center, maintain appropriate spacing from the bottom of the image - Must have decorative elements: at least one of lines/borders/small icons/light effects
- Color contrasts with the background but is not harsh
Style layer: Platform style
The description keywords for platform style uniformly come from references/cover-styles.md 's "Platform Style" section; directly take and use the corresponding keyword string for the target platform, and do not maintain a copy in this file to avoid drifting from the reference file.
Visual layer: Genre + composition
From references/cover-styles.md read the style tags, colors, characters, and background descriptions corresponding to the genre.
Composition variants (output 2-3 options for the first time):
| Option | Composition | Suitable genres |
|---|---|---|
| A | Character close-up + scene | Universal for all genres |
| B | Full-body portrait + dynamic pose | Fantasy, urban, western fantasy |
| C | Pure scene/atmosphere image | Suspense, sci-fi, historical |
Complete prompt template
Chinese web novel cover design, [平台风格].
Title text '{书名}' at top center in [书名字体风格].
Author name '{作者名}' at bottom center in [作者名字体风格 — 从上表选择].
[题材风格标签]. [人物描述]. [背景描述].
[色彩指令]. [光效指令].
Professional book cover, high detail digital painting, portrait [平台比例：番茄=3:4，默认=2:3] ratio, keep title and author name inside the central safe area away from edges (inner ~85%), no watermark
Prompt techniques (verified in practice)
- The more specific the character description, the better: specify every dimension including clothing, pose, hairstyle, expression, and props
- Background layering: foreground (character) → midground (scene) → background (atmosphere)
- Light effects mean specifying the light source direction + color (e.g.,
dramatic golden light from above） - Use
digital painting styleinstead ofphoto, to avoid a realistic photo feel
Step 4: Call the API and save
gpt-image-2 always returns base64; do not include response_formatin the request body (an old DALL-E parameter, not supported by the gpt-image series).$PROMPT The complete prompt assembled for the "Build Prompt" step.
Choose one of two invocation methods: if not set, REF_IMAGE → use "Text-to-Image"; if set → use "Image-to-Image".
Text-to-Image (default)
set -euo pipefail
: "${GPT_IMAGE_API_KEY:?请设置 export GPT_IMAGE_API_KEY=你的key}"
: "${PROMPT:?请先 export PROMPT=构建提示词步骤拼好的完整提示词}"
BASE_URL="${GPT_IMAGE_BASE_URL:-https://api.openai.com/v1}"
MODEL="${GPT_IMAGE_MODEL:-gpt-image-2}"
SIZE="${GPT_IMAGE_SIZE:-1024x1536}"
BOOK_DIR="${BOOK_DIR:?请先 export BOOK_DIR=./covers/<书名>}"
mkdir -p "$BOOK_DIR/封面"
# 自增版本号，避免覆盖之前生成的封面
i=1
while [ -f "$BOOK_DIR/封面/封面_v${i}.png" ]; do i=$((i+1)); done
OUT="$BOOK_DIR/封面/封面_v${i}.png"
RESP=$(mktemp)
trap 'rm -f "$RESP"' EXIT
# 用 jq 拼 JSON 体，避免 PROMPT 里的引号/换行/中文把 shell 字符串撑破
BODY=$(jq -n \
--arg m "$MODEL" \
--arg p "$PROMPT" \
--arg s "$SIZE" \
'{model:$m, prompt:$p, size:$s}')
curl -fsS --max-time 180 --retry 2 --retry-delay 5 \
"$BASE_URL/images/generations" \
-H "Authorization: Bearer $GPT_IMAGE_API_KEY" \
-H "Content-Type: application/json" \
-d "$BODY" > "$RESP"
# API 出错时早退，避免把 error JSON 当成 base64 写成损坏 PNG
if jq -e '.error' "$RESP" >/dev/null 2>&1; then
echo "API error:" >&2
jq '.error' "$RESP" >&2
exit 1
fi
# `// empty` 让缺失字段输出空串而非 "null"，配合下面的 -s 检查避免写出 3 字节假 PNG
jq -er '.data[0].b64_json // empty' "$RESP" | base64 --decode > "$OUT"
[ -s "$OUT" ] || { echo "empty or malformed output: $OUT" >&2; head -c 300 "$RESP" >&2; exit 1; }
# 落地提示词副本，方便迭代时基于上一次微调
printf '%s\n' "$PROMPT" > "${OUT%.png}.prompt.txt"
file "$OUT"
ls -lt "$BOOK_DIR/封面/"
Image-to-Image (when a reference image is provided)
/v1/images/edits use multipart/form-data，cannot use Content-Type: application/json. For text fields use --form-string(to avoid @ being mistaken for a file reference), for image fields use -F image=@path。
set -euo pipefail
: "${GPT_IMAGE_API_KEY:?请设置 export GPT_IMAGE_API_KEY=你的key}"
: "${PROMPT:?请先 export PROMPT=构建提示词步骤拼好的完整提示词}"
BASE_URL="${GPT_IMAGE_BASE_URL:-https://api.openai.com/v1}"
MODEL="${GPT_IMAGE_MODEL:-gpt-image-2}"
SIZE="${GPT_IMAGE_SIZE:-1024x1536}"
BOOK_DIR="${BOOK_DIR:?请先 export BOOK_DIR=./covers/<书名>}"
REF_IMAGE="${REF_IMAGE:?请先 export REF_IMAGE=本地路径或 URL}"
mkdir -p "$BOOK_DIR/封面"
# 自增版本号
i=1
while [ -f "$BOOK_DIR/封面/封面_v${i}.png" ]; do i=$((i+1)); done
OUT="$BOOK_DIR/封面/封面_v${i}.png"
RESP=$(mktemp)
REF_TMP=""
trap '[ -n "$REF_TMP" ] && rm -f "$REF_TMP"; rm -f "$RESP"' EXIT
# URL 先下载到临时文件，本地路径直接用。用裸 mktemp 以保证 macOS/Linux 行为一致。
case "$REF_IMAGE" in
http://*|https://*)
REF_TMP=$(mktemp)
curl -fsSL --max-time 60 -o "$REF_TMP" "$REF_IMAGE"
REF_LOCAL="$REF_TMP"
;;
*)
[ -f "$REF_IMAGE" ] || { echo "参考图不存在: $REF_IMAGE" >&2; exit 1; }
REF_LOCAL="$REF_IMAGE"
;;
esac
curl -fsS --max-time 240 --retry 2 --retry-delay 5 \
"$BASE_URL/images/edits" \
-H "Authorization: Bearer $GPT_IMAGE_API_KEY" \
--form-string "model=$MODEL" \
--form-string "size=$SIZE" \
--form-string "prompt=$PROMPT" \
-F "image=@$REF_LOCAL" > "$RESP"
if jq -e '.error' "$RESP" >/dev/null 2>&1; then
echo "API error:" >&2
jq '.error' "$RESP" >&2
exit 1
fi
# `// empty` 让缺失字段输出空串而非 "null"，配合 -s 检查避免写出 3 字节假 PNG
jq -er '.data[0].b64_json // empty' "$RESP" | base64 --decode > "$OUT"
[ -s "$OUT" ] || { echo "empty or malformed output: $OUT" >&2; head -c 300 "$RESP" >&2; exit 1; }
printf '%s\n' "$PROMPT" > "${OUT%.png}.prompt.txt"
printf '%s\n' "$REF_IMAGE" > "${OUT%.png}.ref.txt"
file "$OUT"
ls -lt "$BOOK_DIR/封面/"
Step 5: Export platform upload size (when the platform has fixed pixels)
If UPLOAD_SIZEis set (Tomato 600×800), then take the original imagecenter-crop + scaleto the upload size—regardless of whether the output image is 2:3 or 3:4, crop it to the platform's exact pixels, without distortion, to avoid the platform cropping off the book title/pen name again. Keep the original image and save a separate _上传 version:
SRC="${OUT:-$(ls -t "${BOOK_DIR:-.}"/封面/封面_v*.png 2>/dev/null | grep -v _上传 | head -1)}" # 复用「调用 API 并保存」步骤的 $OUT；新 shell 里从 BOOK_DIR 找最新原图
TARGET="${UPLOAD_SIZE:-}" # 番茄=600x800；未设则跳过
if [ -n "$TARGET" ] && [ -f "$SRC" ]; then
UP="${SRC%.png}_上传.png"; W="${TARGET%x*}"; H="${TARGET#*x}"
if command -v magick >/dev/null 2>&1; then M=magick
elif command -v convert >/dev/null 2>&1; then M=convert; else M=""; fi
if [ -n "$M" ]; then
"$M" "$SRC" -resize "${W}x${H}^" -gravity center -extent "${W}x${H}" "$UP" # 缩放填满后居中裁
elif command -v sips >/dev/null 2>&1; then
cp "$SRC" "$UP"
sw=$(sips -g pixelWidth "$UP" | awk '/pixelWidth/{print $NF}')
sh=$(sips -g pixelHeight "$UP" | awk '/pixelHeight/{print $NF}')
if [ $((sw*H)) -ge $((sh*W)) ]; then sips --resampleHeight "$H" "$UP" >/dev/null
else sips --resampleWidth "$W" "$UP" >/dev/null; fi
sips -c "$H" "$W" "$UP" >/dev/null # sips -c 是 高 宽，居中裁
else
echo "无 magick/convert/sips，跳过；手动把 $SRC 居中裁剪+缩放到 $TARGET 再上传" >&2
fi
[ -f "$UP" ] && file "$UP"
fi
The book title/pen name already have a central safe zone reserved in the prompt, so center-cropping will not cut them off.
Step 6: Quality check + iteration
| Check item | Standard |
|---|---|
| Text rendering | The book title is clearly legible, and the font style matches the genre |
| Genre match | The visual style is consistent with the book title's genre |
| Reasonable composition | The subject stands out, and the text does not obscure the core image |
| Platform fit | Matches the cover style and tone of the target platform |
| Platform size | The aspect ratio matches the platform; after scaling to the upload size, the book title and pen name are fully visible and not cropped |
When dissatisfied, adjust direction: change the composition, adjust the color tone, change the font style, or change the platform style.
Reference materials
| File | When to load |
|---|---|
| references/cover-styles.md | Genre→visual style mapping, platform style details, prompt templates |
Language
- Reply in the user's language; use whatever language the user uses
- Chinese replies follow the "Chinese Copywriting Guidelines"