Skip to content

Add Depth Anything 3 and Bernini-R tutorial pages#1148

Open
lin-bot23 wants to merge 4 commits into
Comfy-Org:mainfrom
lin-bot23:docs/berninger-depth3-tutorials
Open

Add Depth Anything 3 and Bernini-R tutorial pages#1148
lin-bot23 wants to merge 4 commits into
Comfy-Org:mainfrom
lin-bot23:docs/berninger-depth3-tutorials

Conversation

@lin-bot23

Copy link
Copy Markdown
Contributor

Summary

This PR adds tutorial documentation for two new open-source templates added in commit 65c22bbd (New Templates #938):

Depth Anything 3 (tutorials/utility/depth-anything-3.mdx)

  • Image and video depth estimation using Depth Anything 3 (ByteDance Seed)
  • Covers all four model variants: Small, Base, Mono-Large, Metric-Large
  • Both image depth estimation and video depth estimation workflows
  • Combined into one doc (same model family, different input types)

Bernini-R (tutorials/video/bernini-r.mdx)

  • Image and video editing using Bernini-R (ByteDance Wan2.2 renderer-only model)
  • Covers all six task types: t2v, v2v, rv2v, r2v, ads2v, img
  • Both image editing and video editing workflows
  • Combined into one doc (same model, different task modes)

Languages

  • English (original), Chinese, Japanese, Korean translations
  • Sidebar navigation updated for all 4 languages in docs.json
  • Translations marked with translationSourceHash / translationFrom for sync tracking

Related

  • Templates: utility_depth_anything3_image_depth_estimation, utility_depth_anything3_video_depth_estimation, video_bernini_r_image_editing, video_bernini_r_video_editing
  • Closes documentation gap for both open-source models

- New: tutorials/utility/depth-anything-3.mdx — Image and video depth
  estimation using Depth Anything 3 (ByteDance Seed)
- New: tutorials/video/bernini-r.mdx — Image and video editing using
  Bernini-R (ByteDance Wan2.2 renderer-only)
- Translated: ZH/JA/KO versions of both tutorials
- Updated: docs.json sidebar navigation for all 4 languages
@coderabbitai

coderabbitai Bot commented Jun 15, 2026

Copy link
Copy Markdown

Review Change Stack

Warning

Review limit reached

@lin-bot23, we couldn't start this review because you've reached your PR review rate limit.

More reviews will be available in 8 minutes and 13 seconds. Learn how PR review limits work.

To continue reviewing without waiting, enable usage-based billing in the billing tab.

⌛ How to resolve this issue?

After more reviews become available, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based credits.

🚦 How do rate limits work?

CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan refill rate.

For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, the refill rate gradually slows as usage increases. The highest same-day bursts are limited more strictly.

Please see our Fair Usage Limits Policy for further information.

ℹ️ Review info
⚙️ Run configuration

Configuration used: Organization UI

Review profile: ASSERTIVE

Plan: Pro Plus

Run ID: fa9af7ff-1eae-4df8-89a6-d1f88cce32bb

📥 Commits

Reviewing files that changed from the base of the PR and between 0d3921e and 0218a6e.

📒 Files selected for processing (6)
  • docs.json
  • ja/tutorials/video/bytedance/bernini-r.mdx
  • ko/tutorials/utility/depth-anything-3.mdx
  • ko/tutorials/video/bytedance/bernini-r.mdx
  • tutorials/video/bytedance/bernini-r.mdx
  • zh/tutorials/video/bytedance/bernini-r.mdx
📝 Walkthrough

Walkthrough

Two new MDX tutorial pages are added — one for Bernini-R (a renderer-only Wan 2.2 video model) and one for Depth Anything 3 (a depth-estimation utility) — each covering model installation, example workflows, and community resources. All pages are provided in English, Chinese, Japanese, and Korean, and their routes are registered in docs.json navigation across all four language sections.

Changes

Tutorial Documentation and Navigation

Layer / File(s) Summary
docs.json navigation registration
docs.json
Registers tutorials/video/bernini-r and tutorials/utility/depth-anything-3 routes (and their zh/, ja/, ko/ equivalents) in the Kandinsky video subgroup and Utility subgroup respectively, plus a minor EOF tweak.
Bernini-R tutorial (English)
tutorials/video/bernini-r.mdx
Adds the full English Bernini-R tutorial: model overview with supported tasks (t2v/v2v/rv2v/r2v/ads2v), weight installation paths (text_encoders/vae/loras/diffusion_models), image-editing and video-editing workflow sections with download/Comfy Cloud cards and step-by-step run instructions, and community resource links.
Bernini-R tutorial (ZH/JA/KO)
zh/tutorials/video/bernini-r.mdx, ja/tutorials/video/bernini-r.mdx, ko/tutorials/video/bernini-r.mdx
Adds Chinese, Japanese, and Korean localizations of the Bernini-R tutorial, each with the same structure as the English source: frontmatter with translation metadata, overview, installation, image- and video-editing workflow sections, and community resources.
Depth Anything 3 tutorial (English)
tutorials/utility/depth-anything-3.mdx
Adds the full English Depth Anything 3 tutorial: DA3 overview with UpdateReminder callout, installation directory layout for Small/Base/Mono-Large/Metric-Large checkpoints, image-depth and video-depth workflow sections with download/Comfy Cloud cards and run steps, a model-variant comparison table, and community resource links.
Depth Anything 3 tutorial (ZH/JA/KO)
zh/tutorials/utility/depth-anything-3.mdx, ja/tutorials/utility/depth-anything-3.mdx, ko/tutorials/utility/depth-anything-3.mdx
Adds Chinese, Japanese, and Korean localizations of the Depth Anything 3 tutorial, each mirroring the English structure with locale-specific frontmatter and translated content throughout.
🚥 Pre-merge checks | ✅ 2
✅ Passed checks (2 passed)
Check name Status Explanation
Linked Issues check ✅ Passed Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check ✅ Passed Check skipped because no linked issues were found for this pull request.

✏️ Tip: You can configure your own custom pre-merge checks in the settings.

✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
✨ Simplify code
  • Create PR with simplified code

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands and usage tips.

@coderabbitai coderabbitai Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 2

🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@ko/tutorials/utility/depth-anything-3.mdx`:
- Around line 118-119: Replace the full-width Chinese punctuation marks in lines
118-119 of the Korean document with standard Korean punctuation. On line 118,
replace the full-width Chinese parentheses ( ) with appropriate Korean
parentheses and replace the full-width Chinese period 。 with standard Korean
punctuation. On line 119, make the same punctuation replacements. This
normalizes the document's punctuation style for consistency with Korean UI copy
conventions.

In `@tutorials/video/bernini-r.mdx`:
- Around line 20-29: The task-type table in the Bernini-R documentation is
missing the `img` task row even though the page documents image editing
capabilities and localized versions include it. Add a new row to the table
(between the header and the existing t2v, v2v, rv2v, r2v, and ads2v entries, or
in the appropriate sorted position) for the `img` task with its corresponding
inputs and description to keep the documentation complete and consistent across
all language versions.
🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

  • Push a commit to this branch (recommended)
  • Create a new PR with the fixes

ℹ️ Review info
⚙️ Run configuration

Configuration used: Organization UI

Review profile: ASSERTIVE

Plan: Pro

Run ID: ee15bd66-19e6-4646-81de-d6fde0528fdf

📥 Commits

Reviewing files that changed from the base of the PR and between d4426ad and 0d3921e.

📒 Files selected for processing (9)
  • docs.json
  • ja/tutorials/utility/depth-anything-3.mdx
  • ja/tutorials/video/bernini-r.mdx
  • ko/tutorials/utility/depth-anything-3.mdx
  • ko/tutorials/video/bernini-r.mdx
  • tutorials/utility/depth-anything-3.mdx
  • tutorials/video/bernini-r.mdx
  • zh/tutorials/utility/depth-anything-3.mdx
  • zh/tutorials/video/bernini-r.mdx

Comment thread ko/tutorials/utility/depth-anything-3.mdx Outdated
Comment thread tutorials/video/bytedance/bernini-r.mdx
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant