Add Wan 2.7 Image Pro Token Station article (en/zh/ja/ko) - #26
Merged
juntao merged 3 commits intoAug 2, 2026
Merged
Conversation
Covers text-to-image generation and prompt-guided editing (including bbox_list region-targeted edits) via qwen/wan-2.7-image-pro, with a branded cover image and sitemap entries for all four languages.
Brings this branch in line with the rule on main: one standalone SVG per output PNG, rasterised with headless Chrome, text burnt in. The committed PNG is also refreshed. It was 0.83% of pixels away from what its own HTML source rendered, so the image on the branch was slightly stale relative to the source that was supposed to produce it. The SVG now reproduces a fresh render of that source with no visible difference (0.00% of pixels past a 64/255 delta). This cover is the first with a linear-gradient tile mosaic, which the converter did not handle. Fixed there and verified against the three covers already on main, which still convert to a byte-level match. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
qwen/wan-2.7-image-pro), Alibaba's professional image generation/editing model, live in all four languages (en/zh/ja/ko)blog/wan-2-7-image-pro-token-station-cover.png) generated from its asset-sources HTML via the standard headless-Chrome pipelineFacts in the article (resolution limits, reference-image count, bbox_list parameter, thinking-mode behavior) were independently verified against Alibaba Cloud's Model Studio docs and cross-referenced against independent model hosts, then adversarially reviewed for accuracy before this PR.
Test plan
npm run buildsucceeds and generates/blog/wan-2-7-image-pro-token-station[-zh|-ja|-ko].html