@wji.ai/cli 0.5.0 → 0.5.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -0,0 +1,124 @@
1
+ # Content craft — hooks, loops, overlays, captions, covers, carousels
2
+
3
+ What makes a post perform once the size is right: the first three seconds, the ending that
4
+ re-plays, text that stays inside the safe zone, a caption shaped for each platform's reading
5
+ pattern, a posting slot to start from, a cover that reads at thumbnail size, and a carousel that
6
+ tells one story. Sizes and limits are quoted from platforms-global.md and platforms-china.md,
7
+ not restated here; teaser and poster recipes built on these rules are in repurpose.md.
8
+
9
+ ## The first 3 seconds
10
+
11
+ Feeds decide in the first swipe-length. The product, the face or the question is on screen by
12
+ second 3, in motion, with no logo card, no fade-in and no "hi guys". Hook types, with a line
13
+ each (drama and product examples side by side):
14
+
15
+ | Hook type | Drama teaser | Product / brand |
16
+ | --- | --- | --- |
17
+ | Shocking line, mid-scene | 「你以为我不知道孩子是谁的?」 cut in on the reaction | "This is the last one we could get made." |
18
+ | Result first, cause later | the slap, the arrest, the reveal — then 「三天前…」 | the after-state (clean pan, finished room), then the before |
19
+ | Direct question | 「如果你婆婆当众撕了你的结婚证,你会怎么做?」 | "Why does every white sneaker turn yellow in a month?" |
20
+ | Contradiction / mismatch | the bride in a wedding dress signing divorce papers | a luxury unboxing on a bus |
21
+ | Countdown / stakes | 「还有十分钟,她就要嫁给别人了」 | "Three tests. One survives." |
22
+ | Visual anomaly | one impossible detail in an ordinary frame (a wet footprint indoors) | the product doing the one thing rivals cannot |
23
+ | Named audience | 「二婚的姐妹看过来」 | "If you edit on a phone, watch this." |
24
+
25
+ Rules: one hook per cut, the first frame is already the strongest frame (it is also the cover),
26
+ sound-off comprehension — the hook line is burned in as text. Write 2–3 hooks for the same body
27
+ and let the platform pick (repurpose.md, variants).
28
+
29
+ ## Loop-friendly endings
30
+
31
+ Reels, TikTok and 抖音 count re-watches. End on a frame that matches the first frame (same
32
+ composition, same subject position) so the loop hides the seam; or end one beat *before* the
33
+ answer the hook promised, so the viewer re-watches to catch it; or end on the CTA card that is
34
+ also the cover. Never end on a logo fade or a black frame. For a drama teaser the ending is the
35
+ cut before the payoff plus the line 「主页看全集 / full episode in bio」 (repurpose.md).
36
+
37
+ ## On-screen text and burned subtitles
38
+
39
+ - Keep every word inside the safe zone of the 9:16 diagram (platforms-global.md): headline in the
40
+ upper safe band, subtitles at the lower edge of the safe band (≈y 1100–1240 on 1080×1920), never
41
+ behind the caption or the right rail.
42
+ - Subtitles are burned in (most feeds autoplay muted): 2 lines maximum, ≤ 14 CJK chars or ≤ 32
43
+ Latin chars per line, high-contrast box or stroke, one style for the whole account.
44
+ - Headline type ≥ 60 px on 1080×1920, ≤ 6 words / 8 chars; a second overlay only when the first
45
+ has left. Do not repeat the caption on screen.
46
+ - Text is added after the crop and at the final ratio (ratio-map.md, crop anchoring); text
47
+ generated inside the picture is only for covers that are never cropped again.
48
+ - 「AI生成」 label where required (platforms-china.md) is the platform's toggle, not an overlay
49
+ you design — but do not place other text where the platform paints its label (top-left on most
50
+ Chinese apps).
51
+
52
+ ## Caption structure per platform
53
+
54
+ | Platform | Structure | Hashtags / tags | Length notes |
55
+ | --- | --- | --- | --- |
56
+ | Instagram | hook line (shown before "more") → 2–4 short lines → CTA (save / share / comment) | **≤5** (Dec 2025 cap) — 3 niche + 2 broad | 2,200 max; the first 125 chars are the post |
57
+ | TikTok / 抖音 | one-line hook + a question that invites comments | 3–5 hashtags / 话题, one is the series tag | 4,000 max on TikTok; 抖音 shows ≈20 chars of title |
58
+ | YouTube | title ≤ 60–70 chars shown; description: 2-line summary, links, chapters, disclosure | 3–5 hashtags at the end of the description | title 100 hard cap |
59
+ | Facebook | short hook, link in the first comment or the post, CTA | 1–3 | shares outweigh hashtags |
60
+ | X | the hook is the whole post; thread for detail | 1–2 or none | 280 |
61
+ | LinkedIn | hook in the first two lines → line-broken story → question → 3 hashtags | 3 | 3,000; "see more" after ≈3 lines |
62
+ | Pinterest | keyword title ≤ 100, description with 2–3 search phrases | none | description 500–800 *(verify)* |
63
+ | Threads | one sentence; the picture carries the rest | none | 500 |
64
+ | 小红书 | 标题 ≤ 20 with the keyword first → 正文 in short lines with emoji markers → 话题 tags | keyword + 3–6 话题 (#…#) | 正文 1,000 (长文 6,000) |
65
+ | 视频号 / 公众号 | one-line 描述 with 话题; the article's first line is the hook | 1–3 话题 | limits not confirmed |
66
+ | B站 | 标题 with the series and episode number; 简介 with timestamps | tags on upload (platform field) | limits not confirmed |
67
+
68
+ A CTA is one verb: 关注 / follow, 主页看全集 / full episode in bio, save, comment the answer.
69
+ Platform buttons (shop, link, subscribe) are not drawn into the picture.
70
+
71
+ ## Posting-time starting points
72
+
73
+ Sprout Social 2026 aggregates, to be treated as **starting points** and replaced by the
74
+ account's own insights after two weeks: Instagram Mon–Thu 10:00–15:00; TikTok Wed 14:00–17:00;
75
+ LinkedIn Tue 11:00–17:00. Local time of the audience, not of the account. Other platforms and
76
+ the Chinese apps: not confirmed in the research — plan lunchtime (12–13) and evening (20–22)
77
+ slots in the audience's time zone and measure. Series content posts at the same slot every
78
+ time; the second post of a series goes out within 24 h of the first while the hook is fresh.
79
+
80
+ ## Cover and thumbnail design
81
+
82
+ - **Face + ≤ 4 words** (≤ 8 CJK chars): the face at 40–60 % of the frame height, looking at the
83
+ camera or at the text; the words in one colour band, one weight.
84
+ - **High contrast**: light text on a darkened lower third or dark text on a light band; check
85
+ it at 120 px wide (the 小红书 / 快手 tile is half a phone).
86
+ - **One template per series**: same title position, same colour, same type; the episode number
87
+ changes, nothing else. Recognition beats novelty in a grid.
88
+ - **Ratio per platform** (ratio-map.md): 16:9 1280×720 YouTube; 3:4 小红书 / IG grid; 9:16 Reels
89
+ / TikTok / 抖音 with the text in the centre 60 % because the grid crops to a taller tile;
90
+ 1146×717 B站 with the bottom-left clear; 6:7 视频号 composed for its 1:1 share crop.
91
+ - Covers are generated **with** the text only at the final ratio (nano-banana-pro, gpt-image-2.5
92
+ or seedream-5-pro for reliable multilingual type); every other size gets the text overlaid
93
+ after the crop.
94
+
95
+ ## Carousel / 图文 storytelling
96
+
97
+ 1. **Cover as hook** — the question, the contrast or the result; it must work alone in the feed.
98
+ 2. **One idea per card**, one line of text per card, the same layout grid on every card.
99
+ 3. **Escalate**: cards 2–N answer the cover in order of surprise, not of logic; the strongest
100
+ proof sits two cards before the end.
101
+ 4. **Last card = CTA** (follow, save, 主页看全集, 领取), in the same template as the cover so the
102
+ loop back to card 1 feels designed.
103
+ 5. **One ratio for the whole set** (IG ≤ 20 slides, 小红书 ≤ 18 images, TikTok photo mode ≤ 35):
104
+ generate every card at the same `ratio` and crop to the same box.
105
+ 6. Caption repeats the cover's keyword in the first line; on 小红书 the 话题 tags close the body.
106
+
107
+ ## Trending audio
108
+
109
+ Trending sounds lift reach on TikTok / 抖音 / Reels, but a business account may only use
110
+ tracks from the platform's **commercially licensed library**; personal-account sounds are
111
+ muted or the post is removed when the account is business-typed. AI-generated soundtracks
112
+ (Seed Audio, generated per teaser) avoid the problem and can be reused across the series.
113
+ Never lip-sync a drama clip to a licensed pop song for a paid promotion.
114
+
115
+ ## What to avoid
116
+
117
+ - A logo intro, a fade-in, a title card before the hook.
118
+ - Letterboxed 16:9 inside a 9:16 post (regenerate — ratio-map.md).
119
+ - Text in the top 270 px or the bottom 670 px of a vertical frame; text under the right rail.
120
+ - More than 5 hashtags on Instagram; hashtag walls anywhere; hashtags that do not exist yet.
121
+ - Sub-1080-px sources, upscaled 1K frames, JPEG re-compression of a re-compression.
122
+ - Cross-platform reposts with the other platform's watermark or overlay language.
123
+ - Engagement bait ("like if…", fake polls), fake countdowns, fake UI buttons drawn into the frame.
124
+ - Claiming AI footage is real footage; skipping the AI label where it is required.
@@ -0,0 +1,171 @@
1
+ # Plan template — the post spec sheet
2
+
3
+ One spec sheet per post (one platform × one surface × one asset). It is written before any
4
+ generation, filled from the platform row (platforms-global.md / platforms-china.md), the ratio
5
+ row (ratio-map.md) and the craft rules (content-craft.md); the campaign's sheets together are
6
+ the deliverables checklist of repurpose.md. The block below is the template; after it, one
7
+ filled example — a 3-episode 短剧 launch on 小红书, 抖音 and Instagram Reels with a teaser and a
8
+ poster per platform. Every figure in a sheet is copied from a reference row or marked
9
+ "not confirmed"; nothing is invented in the sheet.
10
+
11
+ ## Fields
12
+
13
+ | Field | Meaning | Where it comes from |
14
+ | --- | --- | --- |
15
+ | campaign | name of the launch / series / promotion | the user |
16
+ | platform | 小红书, 抖音, Instagram … | the user |
17
+ | surface | the row: 图文, video note, Reels, Stories, thumbnail … | platform file |
18
+ | ratio | delivered ratio | platform row |
19
+ | px | delivered pixel size | platform row |
20
+ | duration cap | the surface's cap and the planned length | platform row; content-craft.md |
21
+ | safe zone | the pixel bands text and faces avoid | platform row / 9:16 diagram |
22
+ | source asset | episode + segment ids, KV id, uploaded file | short-drama storyboard / ads brief / user assets |
23
+ | generation plan | model, `ratio`, `resolution`, `duration`, references (`@imageN`), prompt notes (framing sentence) | ratio-map.md |
24
+ | crop | native ratio → target px, anchor | ratio-map.md, crop anchoring |
25
+ | cover | file or "first frame"; template name | content-craft.md, covers |
26
+ | caption | hook line + body + CTA, within the limit | content-craft.md, captions |
27
+ | hashtags | count and list, within the cap | content-craft.md |
28
+ | CTA | one verb | the brief / series plan |
29
+ | posting slot | day + time in the audience's time zone; "starting point" or "from insights" | content-craft.md, posting times |
30
+ | disclosure | the platform's AI toggle and its state; 「AI生成」 for China | platforms-china.md; repurpose.md §3 |
31
+ | status | planned · quoted · generated · cropped · overlaid · scheduled · posted | the work |
32
+
33
+ ## Template block
34
+
35
+ ```
36
+ campaign:
37
+ platform:
38
+ surface:
39
+ ratio:
40
+ px:
41
+ duration cap: (surface cap) / planned:
42
+ safe zone:
43
+ source asset:
44
+ generation plan:
45
+ model:
46
+ ratio:
47
+ resolution:
48
+ duration:
49
+ references: @image1 = … · @image2 = …
50
+ prompt notes:
51
+ crop: native → target, anchor:
52
+ cover:
53
+ caption:
54
+ hashtags: (n / cap)
55
+ CTA:
56
+ posting slot:
57
+ disclosure:
58
+ status:
59
+ ```
60
+
61
+ ## Filled example — 《穿越战神》 3-episode launch, 小红书 + 抖音 + Instagram Reels
62
+
63
+ Six sheets: a teaser and a poster per platform. Beats and references are the same across the
64
+ three teasers; only the ratio (all 9:16 here), the copy and the covers differ.
65
+
66
+ ```
67
+ campaign: 穿越战神 E01–E03 launch, week 1
68
+ platform: 抖音
69
+ surface: video
70
+ ratio: 9:16
71
+ px: 1080×1920
72
+ duration cap: 60 min (verify) / planned: 30 s
73
+ safe zone: pixel bands not confirmed for 抖音 — using the 9:16 diagram union: x 120–960, y 270–1248
74
+ source asset: E01 storyboard segments 03 (turn), 05 (爽点), 07 (cliff); character sheets C01, C02; scene sheet S02 (the ancestral hall)
75
+ generation plan:
76
+ model: seedance-2.5-ref
77
+ ratio: 9:16
78
+ resolution: 1080p
79
+ duration: 4 segments × 7–8 s (hook 3 s inside segment 1)
80
+ references: @image1 = C01 sheet · @image2 = C02 sheet · @image3 = S02 sheet · @audio1 = C01 voice sample
81
+ prompt notes: vertical, faces at the upper third, hall built in depth (pillar foreground, altar behind); hook variant A = the line 「跪下的应该是你」 cut in cold; subtitles burned in at y 1100–1240
82
+ crop: none (video is regenerated at 9:16)
83
+ cover: first frame of variant A, title template 「穿越战神 · 第1集」 in the centre 60 %
84
+ caption: 「跪下的应该是你。」 穿越战神 第1集 — 他回来了,这次跪的是谁? 主页看全集
85
+ hashtags: 4 / no fixed cap: #穿越战神 #短剧 #逆袭 #第1集
86
+ CTA: 主页看全集
87
+ posting slot: Wed 20:00 CST — not confirmed for 抖音, starting point; replace from insights after week 1
88
+ disclosure: 「AI生成」 toggle on (标识办法 2025-09-01)
89
+ status: quoted
90
+ ```
91
+
92
+ ```
93
+ campaign: 穿越战神 E01–E03 launch, week 1
94
+ platform: 小红书
95
+ surface: 图文 (poster + 3 cards)
96
+ ratio: 3:4
97
+ px: 1242×1660
98
+ duration cap: — / 4 images (≤ 18)
99
+ safe zone: title inside the middle 70 %; the tile is half a screen
100
+ source asset: E01 爽点 keyframe (C01 standing over C02 in the hall); scene sheet S02
101
+ generation plan:
102
+ model: nano-banana-pro
103
+ ratio: 3:4
104
+ resolution: 2K
105
+ references: @image1 = C01 sheet · @image2 = C02 sheet · @image3 = S02 sheet
106
+ prompt notes: poster: two figures, C01 lit from the altar candles, title band lower third with 「穿越战神」 + 「第1集 · 跪下的应该是你」 rendered in the picture; cards 2–4 without text (overlaid after)
107
+ crop: 3:4 2K frame → cover-fit to 1660 high → trim 1–2 px each side → 1242×1660
108
+ cover: card 1 (the poster) — template 「剧名 / 第N集 / one-line hook」
109
+ caption: 标题 (18 chars): 穿越战神|第1集他回来了跪的是谁 · 正文: 3 short lines with emoji markers, the keyword 穿越战神 in line 1, 主页看全集 as the last line
110
+ hashtags: 6 / no fixed cap: #穿越战神 #短剧推荐 #逆袭 #穿越 #第1集 #AI短剧
111
+ CTA: 关注 + 主页看全集
112
+ posting slot: Thu 12:30 CST — not confirmed for 小红书, starting point
113
+ disclosure: 「AI生成」 toggle on
114
+ status: planned
115
+ ```
116
+
117
+ ```
118
+ campaign: 穿越战神 E01–E03 launch, week 1
119
+ platform: Instagram
120
+ surface: Reels
121
+ ratio: 9:16
122
+ px: 1080×1920
123
+ duration cap: 3 min in-app / planned: 30 s
124
+ safe zone: Meta unified (Mar 2026): 269 px top, 384–672 px bottom, 65 px sides
125
+ source asset: the 抖音 teaser's segments (same references), English subtitle layer regenerated
126
+ generation plan:
127
+ model: same clips as 抖音 (no new generation); overlay layer in English at the final ratio
128
+ ratio: 9:16
129
+ resolution: 1080p
130
+ duration: 30 s
131
+ references: —
132
+ prompt notes: hook variant B for this market: the result-first cut (the kneel) before the line
133
+ crop: none
134
+ cover: first frame of variant B; title in the centre — the grid tile is 3:4
135
+ caption: "You should be the one kneeling." Ep 1 of 穿越战神 — full episode in bio.
136
+ hashtags: 5 / 5: #shortdrama #aidrama #cdrama #reels #ep1
137
+ CTA: full episode in bio
138
+ posting slot: Tue 12:00 local — Sprout 2026 starting point (Mon–Thu 10–15)
139
+ disclosure: Meta AI label per policy (auto-detected from Jun 2026; state it in the caption as well)
140
+ status: planned
141
+ ```
142
+
143
+ ```
144
+ campaign: 穿越战神 E01–E03 launch, week 1
145
+ platform: Instagram
146
+ surface: feed poster (4:5)
147
+ ratio: 4:5
148
+ px: 1080×1350
149
+ duration cap: —
150
+ safe zone: avoid the outer 3 % per side (3:4 grid crop since Jan 2025)
151
+ source asset: the 小红书 poster's references
152
+ generation plan:
153
+ model: nano-banana-pro
154
+ ratio: 4:5
155
+ resolution: 2K
156
+ references: @image1 = C01 sheet · @image2 = C02 sheet · @image3 = S02 sheet
157
+ prompt notes: same composition as the 3:4 poster; English title band 「WARLORD RETURNS · EP 1」 rendered in the picture
158
+ crop: none (4:5 is native to nano-banana-pro)
159
+ cover: itself
160
+ caption: hook line + 2 lines + "full episode in bio"
161
+ hashtags: 5 / 5
162
+ CTA: full episode in bio
163
+ posting slot: with the Reel, same day
164
+ disclosure: Meta AI label per policy
165
+ status: planned
166
+ ```
167
+
168
+ The 抖音 poster sheet mirrors the 小红书 one at 9:16 (a native 9:16 generation, title in the
169
+ centre 60 %), and the 抖音 teaser variant C (the direct question hook) is a fourth video sheet
170
+ with only the hook segment regenerated. Six sheets, one references set, two image generations
171
+ per ratio, four video segments plus two extra hook segments — that is the whole quote.
@@ -0,0 +1,94 @@
1
+ # Platform specs — China (抖音, 快手, 小红书, 视频号, B站, 微博, 微信公众号)
2
+
3
+ The same table shape as platforms-global.md for the mainland platforms: per surface, the ratio
4
+ and pixel size, duration and file caps, the safe zone, the text limits, and the conventions that
5
+ decide whether a post is read at all. Chinese trade terms are kept in Chinese (图文, 封面, 话题,
6
+ 标题) because that is how the platform's own upload screens name them. Rows marked *(verify)*
7
+ had conflicting figures in the 2025–2026 research; "not confirmed" means no figure was found —
8
+ say so in the plan rather than guess. Generation ratios and crop boxes per row are in
9
+ ratio-map.md.
10
+
11
+ ## 抖音 (Douyin)
12
+
13
+ | Surface | Ratio · px | Duration | File size | Safe zone | Text limits | Notes |
14
+ | --- | --- | --- | --- | --- | --- | --- |
15
+ | Video | 9:16 1080×1920 (16:9 accepted, letterboxed); 30 or 60 fps | 60 min *(verify; older figure 15 min)* | web upload ≤4 GB | pixel bands not confirmed — same layout as TikTok (right rail, bottom caption): use the 9:16 diagram in platforms-global.md until verified | 标题 ≈20 chars visible; 话题 tags (#…#) appended | product or hook inside 3 s; 抖音 ranks completion rate and re-watches |
16
+ | 图文 | 3:4 or 9:16 images, one ratio per post | — | not confirmed | as video | 标题 ≈20 chars | image count cap not confirmed; swipes with music like TikTok photo mode |
17
+ | 封面 | 9:16 frame (a chosen frame or an uploaded cover) | — | not confirmed | profile grid crops to a taller tile — keep cover text in the centre 60 % | cover text ≤ ≈8 chars readable at thumbnail size | series use one template: same title position, same colour band |
18
+
19
+ ## 快手 (Kuaishou)
20
+
21
+ | Surface | Ratio · px | Duration | File size | Safe zone | Text limits | Notes |
22
+ | --- | --- | --- | --- | --- | --- | --- |
23
+ | Video | 9:16 1080×1920 | ≈10 min | 2–3 GB *(verify)* | not confirmed — use the 9:16 diagram | not confirmed | double-column feed on the home tab: the 封面 is a tile, so its text must survive being half-width |
24
+ | 封面 | 9:16 or 3:4 | — | not confirmed | — | not confirmed | one idea, big type, face if there is one |
25
+
26
+ ## 小红书 (Xiaohongshu / RED)
27
+
28
+ | Surface | Ratio · px | Duration | File size | Safe zone | Text limits | Notes |
29
+ | --- | --- | --- | --- | --- | --- | --- |
30
+ | 图文 note | 3:4 1242×1660 (or 1080×1440); 1:1 and 9:16 accepted | — | ≤18 images, ≤20 MB each | the feed card shows the first image at 3:4 — a 1:1 or 9:16 first image is cropped; titles inside the image sit in the middle 70 % | 标题 ≤20 chars; 正文 ≤1,000 (长文 6,000); 话题 tags inside the body | **one ratio per note**: the first image sets the frame for all; the cover is the hook (see content-craft.md) |
31
+ | Video note | 9:16 or 3:4 | ≤15 min | not confirmed | not confirmed — use the 9:16 diagram | 标题 ≤20; 正文 ≤1,000 | 3:4 video shows larger in the two-column feed than 9:16 |
32
+ | 封面 | 3:4 or 9:16 | — | ≤5 MB | two-column feed: the tile is half the screen width — cover text must read at that size | cover text ≤ ≈8 chars, ≤2 lines | 3:4 covers dominate the discovery feed; a 9:16 cover is cropped to 3:4 on the card |
33
+
34
+ ## 视频号 (WeChat Channels)
35
+
36
+ | Surface | Ratio · px | Duration | File size | Safe zone | Text limits | Notes |
37
+ | --- | --- | --- | --- | --- | --- | --- |
38
+ | Feed video | 6:7 1080×1260 (largest in the feed); 9:16 1080×1920; 4:3 1080×810; 1:1 1080×1080; any ratio 0.33–3.0 accepted | web 3 s–8 h; phone ≤60 min | ≤2 GB | 9:16 plays with black bars in the feed until tapped — 6:7 fills the card without bars | 描述 limit not confirmed; 话题 tags supported | 6:7 has no native generation ratio — crop from 3:4 or 1:1 (ratio-map.md) |
39
+ | 封面 | same ratio as the video; **朋友圈 share crops the cover to 1:1** | — | not confirmed | keep the title and face inside the central square of the cover | — | a 6:7 cover loses 90 px top and bottom in the 朋友圈 card |
40
+ | Live / 直播 preview | 9:16 | — | — | — | — | not covered here |
41
+
42
+ ## B站 (Bilibili)
43
+
44
+ | Surface | Ratio · px | Duration | File size | Safe zone | Text limits | Notes |
45
+ | --- | --- | --- | --- | --- | --- | --- |
46
+ | Video | 16:9 1920×1080 or 3840×2160 | not confirmed | not confirmed | — | 标题 and 简介 limits not confirmed | 横屏 first; vertical is accepted but shown pillar-boxed on desktop |
47
+ | 封面 | 1146×717 (≈16:10) or 1920×1200 | — | ≤2–5 MB | **keep the bottom-left corner clear** (duration badge overlays it); the title of the card sits under the cover, not on it | cover text ≤ ≈10 chars | crop from 3:2 or 16:9 — see ratio-map.md |
48
+ | 动态 (dynamic post) | 1:1 or 4:3 images | — | not confirmed | — | not confirmed | nine-grid like 微博 |
49
+
50
+ ## 微博 (Weibo)
51
+
52
+ | Surface | Ratio · px | Duration | File size | Safe zone | Text limits | Notes |
53
+ | --- | --- | --- | --- | --- | --- | --- |
54
+ | 头条文章 cover | 1000×562 (safe area 1000×400) or 900×500 | — | not confirmed | the card crops top and bottom: keep the title inside the middle 400 px | article title limit not confirmed | crop from 16:9 — see ratio-map.md |
55
+ | Post images | not confirmed | — | not confirmed | not confirmed | post text limit not confirmed | nine-grid: the first three images are seen; make the first the hook |
56
+ | Video | *(verify)* | *(verify)* | *(verify)* | — | *(verify)* | the research produced no reliable 2026 figures for 微博 video |
57
+
58
+ ## 微信公众号 (WeChat Official Account)
59
+
60
+ | Surface | Ratio · px | Duration | File size | Safe zone | Text limits | Notes |
61
+ | --- | --- | --- | --- | --- | --- | --- |
62
+ | 头图 / cover | 2.35:1 900×383 — **plus the 1:1 share crop** taken from its centre | — | not confirmed | title and face inside the central 383×383 square so the 1:1 share card still reads | article title limit not confirmed | crop from 21:9 — see ratio-map.md |
63
+ | Secondary cover (次条) | 1:1 200×200, export at 2× (400×400) | — | not confirmed | — | — | small: one object or one face, no text |
64
+ | 图文 body | images the width of the article column; 900 px wide matches the cover width (practice, not a platform rule) | — | not confirmed | — | body length not confirmed | see 图文 layout notes below |
65
+
66
+ 图文 layout notes: the article opens on the cover and the first line, so the first image after
67
+ the title is a second hook, not a decoration; one image per point, captions under images in a
68
+ lighter weight; a share card at the end repeats the CTA; the 1:1 share crop is what most
69
+ readers see first in a chat, so the cover's centre square is the real cover.
70
+
71
+ ## China-specific practice
72
+
73
+ - **「AI生成」 label.** 《人工智能生成合成内容标识办法》 has been in force since 2025-09-01: AI-generated
74
+ or AI-edited video, images and audio carry a visible 「AI生成」 label (most platforms add a
75
+ toggle on upload — switch it on) and the file keeps implicit metadata / watermark marking. Do
76
+ not strip the marking in the crop step; do not describe AI footage as real footage.
77
+ - **Title style.** 小红书 标题 ≤20 chars and the platform hides more; 抖音 shows ≈20. Front-load the
78
+ keyword the search box will match (product, place, problem), then the twist. Number + result
79
+ patterns (「3个…」「第2集…」) and bracketed qualifiers (【】) read as native; clickbait without the
80
+ payoff in the body is down-ranked.
81
+ - **Emoji and keyword conventions.** Emoji as bullet markers at line starts, not inside
82
+ sentences; the body repeats the title's keyword once in the first line; 话题 tags (#…#) go at
83
+ the end of the body, 3–6 on 小红书, and they are searchable — use the platform's suggested
84
+ spellings, not invented ones.
85
+ - **图文 storytelling.** The cover is the hook (question, contrast, result), each following image
86
+ is one idea with one line of text on it, the last image is the CTA (follow / 主页看全集 / 领取).
87
+ One ratio for the whole set, one title template for the whole account.
88
+ - **Cover text is the headline.** On 小红书 and 快手 the tile is half the screen: ≤8 chars, one
89
+ colour band behind the text, face or product filling the rest.
90
+ - **Search first.** 小红书 and 抖音 surface posts by search as much as by feed: the title, the
91
+ cover text and the first body line should agree on one keyword.
92
+ - **Platform video-style borrowing.** 抖音 audiences reject an obvious repost from TikTok (English
93
+ overlays, foreign sounds); regenerate the overlay layer in Chinese rather than translating on
94
+ top of the old one.
@@ -0,0 +1,122 @@
1
+ # Platform specs — global (Instagram, TikTok, YouTube, Facebook, X, LinkedIn, Pinterest, Threads, Snapchat)
2
+
3
+ One table per platform, one row per surface: the ratio and pixel size to deliver, the duration
4
+ and file-size caps, the safe zone where UI covers the picture, the text limits, and what has
5
+ changed recently with the date. Copy the row into the post spec sheet (plan-template.md) before
6
+ generating anything; the generation ratio and crop box for each row is in ratio-map.md, and the
7
+ Chinese platforms are in platforms-china.md. Figures marked *(verify)* were inconsistent between
8
+ sources in the 2025–2026 research; "not confirmed" means the research produced no figure — never
9
+ fill it from memory, say so and let the user check the platform's current help page.
10
+
11
+ ## The 9:16 safe zone (1080×1920) — one diagram for every vertical surface
12
+
13
+ Vertical surfaces all hide the top band behind the status bar and the bottom band behind the
14
+ caption, the sound tag and the action rail on the right. Measured bands, in pixels of a
15
+ 1080×1920 frame:
16
+
17
+ ```
18
+ y 0 ┌────────────────────────────┐
19
+ │ ▒ top band: Meta 14 % = 269 px (Stories / Reels, unified Mar 2026)
20
+ │ TikTok 108 · IG Reels 220 · Snapchat 150
21
+ y 270 ├────────────────────────────┤ ▒ right rail (likes / comments / share):
22
+ │ │ TikTok 120 px · Meta 6 % = 65 px
23
+ │ SAFE — faces, headline, │ ▒ left band: TikTok 60 px · Meta 65 px
24
+ │ subtitles, product, │
25
+ │ x 120 → 960 │
26
+ y 1248 ├────────────────────────────┤
27
+ │ ▒ bottom band: Meta 20–35 % = 384–672 px (caption + sound + CTA)
28
+ │ TikTok 320 · IG Reels 420 · Snapchat 330
29
+ y 1920 └────────────────────────────┘
30
+ ```
31
+
32
+ The conservative union — text and faces inside **x 120–960, y 270–1248** — is safe on every
33
+ platform in this file at once, so a single 9:16 master can be posted everywhere. Per-platform
34
+ bands are looser; use them only when a variant is made for one platform.
35
+
36
+ ## Instagram
37
+
38
+ | Surface | Ratio · px | Duration | File size | Safe zone | Text limits | Notes |
39
+ | --- | --- | --- | --- | --- | --- | --- |
40
+ | Feed image | 4:5 1080×1350 (standard); 3:4 1080×1440 (shows uncropped in the grid); 1:1 1080×1080; 1.91:1 1080×566 | — | not confirmed | grid tile is 3:4 since Jan 2025: a 4:5 loses ≈3 % per side, 1:1 ≈12 % per side, 1.91:1 keeps only the centre | caption 2,200; **≤5 hashtags since Dec 2025** | 4:5 fills the most feed height; 1080×1440 may fail via API upload |
41
+ | Feed video | 4:5 or 9:16 | 3 s–60 min | not confirmed | as Reels | caption 2,200; ≤5 hashtags | every feed video is shown as a Reel |
42
+ | Reels | 9:16 1080×1920 | 3 min in-app (Jan 2025); up to 15 min upload *(verify)* | not confirmed | 220 px top, 420 px bottom (IG figure); Meta unified 14 % / 20–35 % / 6 % from Mar 2026 | caption 2,200; ≤5 hashtags | cover frame is cropped to 3:4 in the grid — keep the cover's title in the centre |
43
+ | Stories | 9:16 1080×1920 | 60 s per card | not confirmed | 14 % top and bottom clear (269 px) | sticker text, link sticker | tap-through: one idea per card |
44
+ | Carousel | one ratio for every slide (4:5 recommended) | — | not confirmed | first slide sets the crop for all | caption 2,200; ≤5 hashtags | ≤20 slides; last slide carries the CTA |
45
+ | Profile grid | 3:4 tiles since Jan 2025 | — | — | design covers for the 3:4 tile | — | previews of 9:16 Reels and 1:1 posts are centre-cropped |
46
+
47
+ ## TikTok
48
+
49
+ | Surface | Ratio · px | Duration | File size | Safe zone | Text limits | Notes |
50
+ | --- | --- | --- | --- | --- | --- | --- |
51
+ | Video | 9:16 1080×1920 | ≤60 min upload, 10 min in-app | not confirmed | 108 px top · 320 px bottom · 60 px left · 120 px right | caption 4,000 | product or key message inside 3 s; start in motion |
52
+ | Photo mode | 9:16 (1:1 and 4:5 accepted) | — | not confirmed | as video | caption 4,000 | ≤35 images; swipes like a carousel with music |
53
+ | Cover | first frame or a chosen frame, 9:16 | — | — | profile-grid tile crop not confirmed — keep title text in the centre 60 % of the frame | cover text | face + ≤4 words; the same template across a series |
54
+
55
+ ## YouTube
56
+
57
+ | Surface | Ratio · px | Duration | File size | Safe zone | Text limits | Notes |
58
+ | --- | --- | --- | --- | --- | --- | --- |
59
+ | Long-form | 16:9 1920×1080 or 3840×2160 | 15 min unverified account, 12 h verified | not confirmed | end-screen area in the last 5–20 s | title 100 (≈60–70 shown), description 5,000 | chapters from timestamps in the description |
60
+ | Shorts | 9:16 or 1:1 | ≤3 min (Oct 2024) | not confirmed | pixel bands not confirmed — keep captions above the bottom UI; use the 9:16 diagram | title 100 | a Short is any vertical video ≤3 min with #Shorts optional |
61
+ | Thumbnail | 16:9 1280×720 | — | ≤2 MB | duration badge sits bottom-right; keep that corner clear | — | face + ≤4 words, high contrast; see content-craft.md |
62
+ | Posts (formerly Community tab) | image ratio not confirmed | — | not confirmed | — | not confirmed | renamed from "Community" to "Posts"; polls, images, text |
63
+ | End screens | inside the 16:9 frame | last 5–20 s of videos ≥25 s | — | elements occupy the frame — no important picture behind them | — | ≤4 elements (video, playlist, subscribe, link) |
64
+
65
+ ## Facebook
66
+
67
+ | Surface | Ratio · px | Duration | File size | Safe zone | Text limits | Notes |
68
+ | --- | --- | --- | --- | --- | --- | --- |
69
+ | Feed image | 4:5 1080×1350 or 1:1 1080×1080 | — | not confirmed | — | post text not confirmed | 4:5 fills the most feed height |
70
+ | Feed video | 4:5 or 9:16 | 1 s–240 min | not confirmed | Meta 9:16 bands | not confirmed | **all Facebook video is published as Reels since Jun 2025** |
71
+ | Reels | 9:16 1080×1920 | 3–90 s | not confirmed | Meta unified: 14 % top, 20–35 % bottom, 6 % sides (Mar 2026) | caption not confirmed | same master as Instagram Reels |
72
+ | Stories | 9:16 1080×1920 | 1–60 s | not confirmed | Meta unified bands | sticker text | — |
73
+ | Link preview | 1.91:1 1200×630 (OG image) | — | not confirmed | — | title and description from the page's OG tags | crop from 16:9 — see ratio-map.md |
74
+
75
+ ## X
76
+
77
+ | Surface | Ratio · px | Duration | File size | Safe zone | Text limits | Notes |
78
+ | --- | --- | --- | --- | --- | --- | --- |
79
+ | Image post | 16:9 1600×900 or 1:1 | — | not confirmed | timeline preview crops tall images to 16:9-ish — keep the subject centred | 280 chars (Premium longer) | up to 4 images; the first sets the layout |
80
+ | Video | 16:9 or 1:1, ≤1920×1200 | 2 min 20 s (Premium up to 4 h) | 512 MB | — | 280 chars | autoplays muted — burned subtitles |
81
+
82
+ ## LinkedIn
83
+
84
+ | Surface | Ratio · px | Duration | File size | Safe zone | Text limits | Notes |
85
+ | --- | --- | --- | --- | --- | --- | --- |
86
+ | Image post | 1080×1080 or 4:5 1080×1350 | — | not confirmed | — | 3,000 chars ("see more" after ≈3 lines) | first two lines carry the hook |
87
+ | Link preview | 1.91:1 1200×627 | — | not confirmed | — | OG title / description | crop from 16:9 — see ratio-map.md |
88
+ | Video | 16:9, 1:1 or 9:16 | ≤10 min organic | 5 GB | — | 3,000 chars | muted autoplay — burned subtitles; 3 hashtags |
89
+ | Document / carousel | PDF pages, 1:1 or 4:5 | — | not confirmed | — | — | one idea per page, last page CTA |
90
+
91
+ ## Pinterest
92
+
93
+ | Surface | Ratio · px | Duration | File size | Safe zone | Text limits | Notes |
94
+ | --- | --- | --- | --- | --- | --- | --- |
95
+ | Standard Pin | 2:3 1000×1500 | — | not confirmed | — | title 100; description 500–800 *(verify)* | Idea Pins merged into standard Pins in 2023 |
96
+ | Video Pin | 9:16 (2:3 accepted) | 4 s–15 min | not confirmed | bottom band hides behind the title on the feed card | title 100 | first frame is the cover unless a cover is chosen |
97
+
98
+ ## Threads
99
+
100
+ | Surface | Ratio · px | Duration | File size | Safe zone | Text limits | Notes |
101
+ | --- | --- | --- | --- | --- | --- | --- |
102
+ | Post | 4:5 best; 9:16, 1:1, 16:9 accepted | video ≤5 min | 500 MB | — | 500 chars | text-first feed: the first line is the hook |
103
+
104
+ ## Snapchat
105
+
106
+ | Surface | Ratio · px | Duration | File size | Safe zone | Text limits | Notes |
107
+ | --- | --- | --- | --- | --- | --- | --- |
108
+ | Story / Spotlight | 9:16 1080×1920 | 3–180 s | not confirmed | 150 px top · 330 px bottom | caption not confirmed | full-screen only; no letterboxing |
109
+
110
+ ## Recent changes to keep in mind (dated)
111
+
112
+ | When | Platform | Change | Effect on delivery |
113
+ | --- | --- | --- | --- |
114
+ | Oct 2024 | YouTube | Shorts up to 3 min | drama teasers up to 3 min qualify as Shorts |
115
+ | Jan 2025 | Instagram | profile grid tiles 3:4; Reels 3 min in-app | covers designed for 3:4; 4:5 posts lose ≈3 % per side in the grid |
116
+ | 2025 | YouTube | Community tab renamed Posts | say "Posts" in plans |
117
+ | Jun 2025 | Facebook | every video post is a Reel | there is no separate feed-video spec; use the Reels row |
118
+ | Dec 2025 | Instagram | hashtags capped at 5 per post | captions with more are rejected or trimmed; pick 5 |
119
+ | Mar 2026 | Meta | one unified safe zone for Stories and Reels: 14 % top, 20–35 % bottom, 6 % sides | one 9:16 master serves IG and FB Reels and Stories |
120
+
121
+ Where a row says "not confirmed", the platform may well have a published figure; the research
122
+ did not verify it, so the plan must not state one.
@@ -0,0 +1,100 @@
1
+ # Ratio map — placement size → generation ratio, model, crop box
2
+
3
+ Every image placement in platforms-global.md and platforms-china.md, mapped to the ratio a WJI
4
+ image model actually generates (taken from the model seeds — the model's `ratio` list is the
5
+ law, not the platform's wish) and, where the placement is not a native ratio, to the nearest
6
+ native ratio plus the crop box that reaches the exact pixels. Then the same for video, where
7
+ the rule is different: **video is regenerated at the target ratio from the same references,
8
+ never cropped**. Read this after choosing the surfaces and before writing the generation plan
9
+ in plan-template.md.
10
+
11
+ ## Native image ratios per model (from the seeds)
12
+
13
+ | Model (`model`) | Ratios | Resolution | Refs |
14
+ | --- | --- | --- | --- |
15
+ | nano-banana, nano-banana-pro, nano-banana-2 | auto 1:1 2:3 3:2 3:4 4:3 **4:5** 5:4 9:16 16:9 21:9 9:21 | pro / 2: 1K–4K | 14 (pro / 2), 4 (nano-banana) |
16
+ | nano-banana-2-lite | same minus 9:21 | | |
17
+ | gpt-image-2 | auto 1:1 4:3 3:4 16:9 9:16 | 1K / 2K / 4K | 16 |
18
+ | gpt-image-2.5 (sunburst / flare) | gpt-image-2 + **21:9** | 1K / 2K / 4K | 16 |
19
+ | bytedance-seedream-4.5 | 1:1 4:3 3:4 16:9 9:16 | 2K / 4K | |
20
+ | bytedance-seedream-5-lite / 5-pro | seedream-4.5 + 3:2 **2:3** 21:9 | size select; 5-pro layered PNG | |
21
+ | flux-2-flex | 1:1 16:9 3:2 2:3 **4:5** 5:4 9:16 3:4 4:3 | | |
22
+ | marketing-studio-image | auto 1:1 3:2 2:3 4:3 3:4 16:9 9:16 21:9 | 1k / 2k / 4k | 8 |
23
+ | runninghub-midjourney v7 / v8.1 / v8.2 | 1:1 4:3 3:2 16:9 3:4 2:3 9:16 | | |
24
+
25
+ No model generates 1.91:1, 6:7, 16:10, 2.35:1 or any banner size. Those are crops.
26
+
27
+ **Resolution rule.** Pick the resolution whose generated short side is at least the target's short
28
+ side after cover-fit, then downscale; never upscale a 1K frame to a 1242-px-wide note. 1K frames
29
+ (≈1024 on the long side) are too small for every placement in this file except 200×200 and
30
+ 400×400; generate at 2K for everything else and at 4K when the crop keeps less than 60 % of the
31
+ frame.
32
+
33
+ ## Image placements
34
+
35
+ | Placement (file) | Target px | Ratio | Native models | If not native: generate → crop |
36
+ | --- | --- | --- | --- | --- |
37
+ | IG feed / FB feed / Threads | 1080×1350 | 4:5 | nano-banana, nano-banana-pro, nano-banana-2, flux-2-flex | 3:4 → cover-fit to 1080 wide (1080×1440) → crop 45 px top and 45 px bottom |
38
+ | IG feed grid-native, 小红书 图文, 抖音 图文, 小红书 cover | 1080×1440 / 1242×1660 | 3:4 | all models in the table above | 1242×1660 is 4 px off exact 3:4 — cover-fit to height 1660 (1245 wide) → crop 1–2 px each side |
39
+ | IG Reels / Stories / TikTok / Shorts / 抖音 / 快手 covers, Snapchat, 视频号 9:16 | 1080×1920 | 9:16 | all | — |
40
+ | IG 1:1, FB 1:1, LinkedIn post, 视频号 1:1, 公众号 secondary cover, X square | 1080×1080 / 1200×1200 / 400×400 | 1:1 | all | — |
41
+ | YouTube thumbnail, X, B站 video frame, 微博 1000×562 | 1280×720 / 1600×900 / 1920×1080 / 1000×562 | 16:9 | all | 1000×562 is 16:9 to the pixel — resize only; keep the title inside the middle 400 px |
42
+ | Pinterest Pin | 1000×1500 | 2:3 | nano-banana family, seedream-5-lite / 5-pro, flux-2-flex, marketing-studio-image, midjourney | 3:4 → cover-fit to height 1500 (1125 wide) → crop 62 px left, 63 px right |
43
+ | 视频号 4:3, B站 动态 | 1080×810 | 4:3 | all | — |
44
+ | IG landscape | 1080×566 | 1.91:1 | none | 16:9 → cover-fit to 1080 wide (1080×608) → crop 21 px top and bottom |
45
+ | FB / LinkedIn link preview, Google landscape | 1200×630 / 1200×627 / 1200×628 | 1.91:1 | none | 16:9 → cover-fit to 1200 wide (1200×675) → crop 22–24 px top and bottom (45 / 48 / 47 px in total) |
46
+ | 视频号 feed card | 1080×1260 | 6:7 | none | 3:4 → 1080×1440 → crop 90 px top and 90 px bottom (keeps full width); or 1:1 → cover-fit to height 1260 (1260 wide) → crop 90 px each side (keeps full height) |
47
+ | B站 cover | 1146×717 | ≈16:10 | none | **3:2** (closest) → cover-fit to 1146 wide (1146×764) → crop 23 px top, 24 px bottom; or 16:9 (from the master) → cover-fit to height 717 (1275 wide) → crop 64–65 px each side |
48
+ | B站 cover large | 1920×1200 | 16:10 | none | 3:2 → 1920×1280 → crop 40 px top and bottom; or 16:9 → 2133×1200 → crop 106–107 px each side |
49
+ | 公众号 cover | 900×383 | 2.35:1 | none | 21:9 (gpt-image-2.5, nano-banana family, seedream-5-lite / 5-pro, marketing-studio-image) → cover-fit to 900 wide (900×386) → crop 1 px top, 2 px bottom; the 1:1 share crop is the centre 383×383 (x 258–641) — compose for that square |
50
+ | 微博 头条文章 alt | 900×500 | 1.8:1 | none | 16:9 → cover-fit to 900 wide (900×506) → crop 3 px top and bottom |
51
+ | 公众号 secondary | 200×200 (export 400×400) | 1:1 | all | generate 1:1 at 1K, downscale to 400, deliver 400×400 |
52
+
53
+ "Cover-fit" means: scale the generated frame uniformly until it covers the target box, then cut
54
+ what falls outside, anchored as described under "Crop anchoring". One generated frame per ratio,
55
+ never one per pixel size: a single 16:9 frame serves the YouTube thumbnail, X, 微博 and every
56
+ 1.91:1 preview.
57
+
58
+ ## Video placements
59
+
60
+ | Placement | Ratio | Models that generate it natively (`ratio`) | Duration range (`duration`) |
61
+ | --- | --- | --- | --- |
62
+ | Reels, Stories, TikTok, Shorts, 抖音, 快手, 小红书 video, 视频号 9:16, Snapchat, Pinterest video | 9:16 | minimax-h3 (+ -ref), seedance-2.5 (+ -ref), seedance-2.0 family, wan-3.0 (+ -ref, prime), veo-3.1, kling-3, happy-horse | h3 5–15 s · seedance-2.5 4–30 s · seedance-2.0 4–15 s · wan-3.0 2–30 s · veo-3.1 4–8 s · kling-3 3–15 s · happy-horse 3–15 s |
63
+ | YouTube long-form, B站, X, LinkedIn, FB in-stream | 16:9 | all of the above | as above |
64
+ | IG / FB / LinkedIn square, 视频号 1:1, Shorts 1:1, X 1:1 | 1:1 | minimax-h3, seedance-2.5, seedance-2.0, wan-3.0, kling-3, happy-horse (not veo-3.1) | as above |
65
+ | 视频号 4:3 | 4:3 | minimax-h3, seedance-2.5, seedance-2.0, wan-3.0, happy-horse | as above |
66
+ | 小红书 3:4 video, 视频号 tall card, 抖音 图文-style video | 3:4 | minimax-h3, seedance-2.5, seedance-2.0, wan-3.0, happy-horse | as above |
67
+ | Cinematic banner, hero loop | 21:9 | minimax-h3, seedance-2.5, seedance-2.0 | as above |
68
+ | 视频号 6:7, Pinterest 2:3, 1.91:1 previews | — | none | deliver the nearest accepted ratio instead: 视频号 takes 3:4 or 1:1 (0.33–3.0 accepted), Pinterest takes 9:16, link previews take a 16:9 still |
69
+
70
+ Resolutions: minimax-h3 480P / 768P / 2K / 4K; seedance-2.5 480p / 720p / 1080p; wan-3.0 480P /
71
+ 720P / 1080P; seedance-2.0 480p / 720p. Publish 1080p or the model's top tier below it; the
72
+ platform re-encodes anyway.
73
+
74
+ **The video rule.** A 16:9 master cropped to 9:16 loses two thirds of the frame and lands the
75
+ faces under the caption band; a 9:16 master padded to 16:9 is a phone video with bars. So every
76
+ ratio in the placement list is a **new generation**: the same character / scene / product
77
+ references (`@image1` …), the same segment prompt with the framing sentence rewritten for the
78
+ new frame ("vertical, subject centred, head at the upper third, room built in depth"), the same
79
+ `duration`. Cost is one clip per ratio per segment — plan it in repurpose.md, quote it, then
80
+ generate. The only cut permitted on a video is trimming its length.
81
+
82
+ ## Crop anchoring
83
+
84
+ A crop box has an anchor: the point that must stay inside. Decide it per frame before cutting.
85
+
86
+ | Frame content | Anchor | Then |
87
+ | --- | --- | --- |
88
+ | A face (poster, teaser cover, testimonial still) | the face box; eyes at ≈1/3 from the top of the target | crop from the bottom first, then the top; never cut the chin or the hairline |
89
+ | Two faces | the midpoint between them, both boxes inside | if both cannot fit, regenerate the frame tighter rather than cut one out |
90
+ | Product / packshot | the product's centre; the whole product plus its shadow inside | crop the sides symmetrically; on 1.91:1 previews keep the label readable at 600 px wide |
91
+ | Headline zone (key visual with text) | the text block plus its margin | text is rendered into the picture only on the final ratio — on crops, generate without text and overlay after |
92
+ | Scene / landscape | the horizon or the main light | side crops are free; top / bottom crops keep the horizon off the edge |
93
+
94
+ After the crop, re-check the target's safe zone (platforms-global.md / platforms-china.md):
95
+ a 6:7 视频号 cover is shared to 朋友圈 as its centre 1:1, so the face has to sit inside that
96
+ square; a 900×383 公众号 cover is read as its centre 383×383 in chats; a 4:5 IG post loses ≈3 %
97
+ per side in the 3:4 grid; a 16:9 thumbnail keeps the bottom-right corner clear for the duration
98
+ badge and a B站 cover the bottom-left. When the anchor cannot survive the crop, the answer is a
99
+ new generation at the closer native ratio (3:4 instead of 1:1 for 6:7, 3:2 instead of 16:9 for
100
+ 1146×717), not a smaller face.