Changelog

Every released update, newest first. Find new tools, new models, and the little improvements that keep you creating.

v1.46.0

Latest release

Preview Seedance drafts through SVRouter before finalizing.

Added
  • Preview Seedance 2.5 videos in Draft Mode on SVRouter, then create a separate 1080p final from your chosen draft.

v1.45.0

More ways to guide your next video.

Added
  • Create videos with Kling 4.0 on APIMart, including ordered keyframes, references, editing, and extension.
  • Choose Prime alongside Standard for Wan 3.0 on DashScope.
  • Animate one image without a prompt or combine images and optional MP3 references with Vidu Q4 Preview on APIMart.

v1.44.0

Preview Seedance drafts, then create HD finals.

Added
  • Choose Draft in the Seedance 2.5 resolution menu on BytePlus to preview a 480p video with your usual generation controls.
  • Select a saved draft and click Generate 1080p to create a separate final video. Expired or inaccessible drafts show the usual generation error.

v1.43.1

Fresh package for another Community release review.

Changed
  • Repackage the existing plugin for a new automated Community release review.

v1.43.0

More image and video choices through SVRouter.

Added
  • Use GPT Image 2.5 through SVRouter with Flare and Sunburst variants.
  • Add Fast H3 Omni through a configured SVRouter Reactor gateway for video generation with image and audio references.
Fixed
  • Keep numbered audio references aligned with their visible order.

v1.42.0

Create voice references with BreezeBlue audio candidates.

Added
  • Design voices with Breeze TTS 2 Multilingual on BreezeBlue, choosing one, two or three audio candidates per request.
  • Keep the voice description in an upstream text node and the spoken script in the current node, then use each audio candidate as a video voice reference.

v1.41.0

Seedream 5.0 Pro and Flash join the image lineup.

Added
  • Generate images with Seedream 5.0 Pro and Seedream 5.0 Flash on Volcengine and BytePlus, using up to 10 reference images.
  • Use a custom model ID or inference endpoint for every Volcengine and BytePlus model.
Fixed
  • Save Seedream images with the correct file type and show Volcengine and BytePlus error details.
  • Keep a failed generation marked as failed, with its error, while other generations start on the same canvas.

v1.40.3

Keep background checks steady across window changes.

Fixed
  • Keep background request timeouts consistent while switching or closing popout windows.

v1.40.2

Clearer generation status and reliable custom endpoints.

Fixed
  • Use custom BytePlus endpoints with the selected Seedance model's modes and output options.
  • See generation stages and open paused or failed task details from either canvas control.
  • Resume paused checks for the same task without submitting another generation.
  • Keep voice-design previews within provider limits while preserving the final speech text.

v1.40.1

Pick up your work where you left off.

Fixed
  • Resume saved audio and video tasks after restarts or temporary connection problems.
  • Use Resume checking to finish tasks that need attention.
  • Keep shared source files available when migrating canvas assets.

v1.40.0

More ways to make music and motion.

Added
  • Create MiniMax H3 videos through Pika with image, video, or audio references.
  • Generate Sonilo Music from a prompt or connect a video to create a soundtrack.

v1.39.1

Clearer messages when a task needs attention.

Fixed
  • See more useful provider error details for SVRouter video tasks.

v1.39.0

Fresh image tools and HappyHorse video.

Added
  • Explore GPT Image 2.5 through APIMart with speed and editing variants.
  • Create and edit videos with HappyHorse 1.1 through DashScope.
  • Use custom BytePlus model endpoints where supported.

v1.38.0

Follow your image generation through SVRouter.

Changed
  • Track image generation progress through SVRouter with supported providers.

v1.37.0

More control over your Midjourney images.

Added
  • Use Midjourney V8.2 through Legnext with standard or 2K HD output.
  • Shape results with stylize, chaos, raw style, stop, and weird controls.

v1.36.2

Sharper Seedance output and connected references.

Fixed
  • Generate Seedance 2.5 video at 1080p.
  • Use connected image references in agent generation workflows.

v1.36.1

Give portrait videos their full frame.

Fixed
  • View portrait videos at their original proportions in full screen.

v1.36.0

New Grok image and video options.

Added
  • Create images with Grok Imagine Image 2.0 through xAI.
  • Use Grok Video 1.5 for supported xAI video modes.
  • Choose the image ratios, quality, and resolution your provider supports.

v1.35.0

MiniMax H3 brings references into motion.

Added
  • Create MiniMax H3 videos through APIMart.
  • Guide generation with images, video, or audio references on supported modes.

v1.34.2

Another provider for your Seedance work.

Added
  • Use Seedance 2.5 through SVRouter.

v1.34.1

Connect your preferred BytePlus video endpoint.

Added
  • Configure the BytePlus video endpoint in provider settings.

v1.34.0

Create longer scenes with Seedance 2.5.

Added
  • Use Seedance 2.5 through Volcengine or BytePlus.
  • Create, extend, or edit videos with supported reference modes and durations up to 30 seconds.

v1.33.0

Build a scene with Wan 3.0.

Added
  • Create Wan 3.0 videos through DashScope.
  • Use images, video, audio, or a PDF as references in supported modes.

v1.32.0

Bring your canvas to life with music.

Added
  • Generate Mureka Music from a prompt, lyrics, or an instrumental direction.
  • Keep track of music tasks while the provider works.

v1.31.3

A small update for SVRouter connections.

Fixed
  • General bug fixes.

v1.31.2

Updated controls for Kling through Pika.

Fixed
  • See the current supported Kling 3.0 controls when using Pika.

v1.31.1

A little polish for your creative workspace.

Fixed
  • General bug fixes.

v1.31.0

More video options and local image cleanup.

Added
  • Use Kling video generation through Pika.
  • Choose 4K output for supported Seedance 2.0 connections.
  • Try the local NLM 35 denoise option with a configured local service.

v1.30.1

A little polish for your creative workspace.

Fixed
  • General bug fixes.

v1.30.0

A new voice for the same performance.

Added
  • Change a voice with ElevenLabs while preserving its timing and delivery.
  • Connect a voice reference to your audio node to guide the result.

v1.29.2

Keep the image you chose to create.

Fixed
  • Save individual Legnext image results to your canvas.

v1.29.1

Refinements for FLUX through fal.ai.

Fixed
  • General bug fixes.

v1.29.0

Another home for your FLUX images.

Added
  • Use FLUX.2 Klein 9B through fal.ai for text and reference image generation.

v1.28.0

Kling Omni video meets FLUX image tools.

Added
  • Create Kling 3.0 Omni videos with supported image, video, and editing references.
  • Generate and denoise images with FLUX.2 Klein 9B through BFL or RunPod.
  • Choose multi-shot and audio settings for supported Kling workflows.

v1.27.3

Refinements for automatic video duration.

Fixed
  • General bug fixes.

v1.27.2

Refinements for your image size controls.

Fixed
  • General bug fixes.

v1.27.1

Refinements for GPT Image generation.

Fixed
  • General bug fixes.

v1.27.0

More ways to connect GPT Image.

Added
  • Use the GPT Image 2 Official option through supported gateway providers.
  • Choose quality and resolution controls for supported connections.

v1.26.3

Keep canvas work in its own space.

Fixed
  • General bug fixes.

v1.26.2

Refinements for reference-based image editing.

Fixed
  • General bug fixes.

v1.26.1

A little polish for your creative workspace.

Fixed
  • General bug fixes.

v1.26.0

Guide a character with a motion reference.

Added
  • Use Kling Motion Control with a character image and a reference video.
  • Choose supported orientation and audio options through Kling or APIMart.

v1.25.0

Bring more references into your video workflow.

Added
  • Use image, audio, and video references with supported Seedance gateway connections.
  • Explore supported Grok video reference and extension modes through the gateway.

v1.24.0

A gateway for more of your models.

Added
  • Connect an SV NewAPI provider for supported image, video, text, and audio models.
  • See the generation modes and controls supported by each provider connection.

v1.23.0

Pack up bigger canvases for the journey.

Added
  • Export larger canvases with their media as a .bragi package.
  • Review asset counts and package size before choosing where to save.
  • Adjust sound-effect duration within the range supported by your provider.

v1.22.0

More ways to create with Wan video.

Added
  • Create, extend, and edit videos with Wan 2.7 through DashScope.
  • Configure your preferred DashScope endpoint in provider settings.

v1.21.3

Refinements for video references in text generation.

Fixed
  • General bug fixes.

v1.21.2

Refinements for reference asset uploads.

Fixed
  • General bug fixes.

v1.21.1

A little polish for your creative workspace.

Fixed
  • General bug fixes.

v1.21.0

A lighter way to explore with Seedream.

Added
  • Generate Seedream 5.0 Lite images through Volcengine or BytePlus.
  • Choose 2K, 3K, or 4K output for supported connections.

v1.20.0

New image options and canvas video editing.

Added
  • Explore Z-Image and Qwen Image Edit through MuleRouter.
  • Create Gemini Omni videos through SuChuang.
  • Trim a video or capture a frame directly from its canvas node.

v1.19.1

A smoother space for image annotation.

Fixed
  • General bug fixes.

v1.19.0

Explore scenes with Gemini Omni video.

Added
  • Use Omni-Flash-Ext through APIMart with supported text, image, and video references.

v1.18.0

Mark up your ideas on the canvas.

Added
  • Annotate images with boxes, numbers, and mosaic regions.
  • Save annotations or undo your edits before leaving the tool.

v1.17.2

Another connection for your Seedance videos.

Added
  • Use Seedance 2.0 and Seedance 2.0 Fast through Token360.

v1.17.1

Explore Wan video through MuleRouter.

Added
  • Connect MuleRouter for supported Wan image-to-video generation.
  • Choose which new models to enable in your workspace.

v1.17.0

Stay current and choose your model connections.

Added
  • Check for plugin updates from the command palette.
  • Choose the models to connect when adding a provider.
  • Manage which provider each enabled model uses.

v1.16.0

Collages and stronger voice cloning.

Added
  • Image collage combines selected image nodes into one new PNG.
  • TokenRouter Seedance can use asset-based references for images, audio, and video.
  • Provider-scoped asset IDs let one image remember separate assets per provider.
  • ElevenLabs and MiniMax can clone voices from upstream audio.
  • ElevenLabs controls add stability, similarity, style, and speed options.
  • Generation parameters support range popovers and number inputs.
Changed
  • GPT Image 2 uses clearer aspect-ratio and image-size handling.
  • Reference thumbnails can show asset IDs from multiple providers.
Fixed
  • GPT Image 2 handles more image proportions reliably.

v1.15.0

Faster large canvases with lazy media.

Added
  • Lazy media loads offscreen images and videos only when they come into view.
  • Thumbnail cache creates lightweight previews for large images.
  • Performance settings let you rebuild or clear thumbnail caches.
Changed
  • Canvas refreshes run after relevant edits instead of constant background scans.
  • Reference thumbnails and audio durations reuse lighter cached work.
Fixed
  • Large media canvases open with less CPU and memory pressure.

v1.14.3

Gemini multimodal refs for text.

Added
  • APIMart can route GPT-5.5 text generation.
  • Gemini 3.5 Flash is available through Google Gemini and TokenRouter.
  • Gemini text generation can use upstream video, audio, and PDF references.
  • Agents can inspect upstream audio and PDF references.
Fixed
  • Gemini text errors show clearer details.

v1.14.2

Clearer APIMart task errors.

Fixed
  • APIMart task failures show readable error details.

v1.14.1

APIMart support for Nano Banana.

Added
  • Nano Banana Pro and Nano Banana 2 can use APIMart as an image provider.

v1.14.0

Unified Qwen voices and voice design.

Added
  • Qwen Voice brings built-in voices, voice references, and designed voices into one model.
  • Voice design lets an upstream text node describe the voice while the current node stays the spoken script.
  • CosyVoice can create designed voices from prompt text.
Changed
  • Voice sources are clearer: Built-in, Voice ref, and Design.
  • Qwen Voice replaces the separate Qwen audio entries.
  • Built-in Qwen voices still use the searchable voice picker.
Fixed
  • Agent audio generation keeps voice reference and design choices.
  • Designed voices keep canvas files smaller.

v1.13.0

Voice picker and cloning for TTS.

Added
  • TTS voice picker lets you search, filter, preview, and choose voices.
  • Voice cloning can reuse a cloned voice from the same reference audio.
  • DashScope audio models add Qwen and CosyVoice generation options.
Changed
  • Audio model names are shorter in the generation bar.
  • Temporary uploads use the new Bragi temp service.
Fixed
  • Voice choices work more reliably across fal-backed audio models.
  • General bug fixes.

v1.12.16

Gemini can read video references.

Added
  • Gemini text generation can use upstream videos as references.
Changed
  • Video references are uploaded through Bragi Relay before Gemini reads them.
Fixed
  • Unsupported text providers now explain when video references are unavailable.

v1.12.15

Safer imports and refreshed OpenAI models.

Changed
  • MCP server starts disabled for new installs.
  • Bragi package import uses a standard file picker.
  • OpenAI text models now include GPT-5.5 and GPT-5.5 Pro.
Fixed
  • OpenAI Pro text generation routes through the right API.
  • Agent edge deletion reports a clear error if an edge remains.
  • The language prompt guides users to switch Obsidian language manually.
  • General bug fixes.

v1.12.14

License update and toolbar polish.

Changed
  • License changed to Mozilla Public License 2.0.
  • Edge, group, and text-node toolbars have a cleaner Bragi layout.
Fixed
  • Remove label now lives in the More menu for labeled edges.
  • Group background controls use the Bragi toolbar icon style.
  • General bug fixes.

v1.12.13

Safer Bragi packages and downloads.

Changed
  • Bragi packages now use a single-file format with embedded assets.
  • Imported package assets are written only to your vault assets folder.
  • Export and media download flows behave more like normal browser downloads.
  • Release downloads are easier to verify.
Fixed
  • General bug fixes.

v1.12.12

Settings import and broader TokenRouter support.

Added
  • Import settings lets you bring in a Bragi Canvas settings file after validation and confirmation.
  • Seedance supports reference-video generation through BytePlus.
  • TokenRouter now covers image, video, and text generation from one provider.
  • HappyHorse video models are available through TokenRouter.
Fixed
  • HappyHorse image-to-video works with reference images.
  • General bug fixes.

v1.12.11

Restored canvas tools and cleaner docs.

Changed
  • Canvas toolbar tools are back for text, media, edges, and groups.
  • The More menu now holds Focus, Set color, and Delete across more selections.
  • Install guidance better matches the current community release.
Fixed
  • Split grid, 360° viewer, Mark, media downloads, and connected duplication are available again.
  • General bug fixes.

v1.12.10

Release packaging for manual installs.

Fixed
  • Release downloads include the expected plugin files.

v1.12.9

Cleaner wording across settings and notices.

Fixed
  • Settings and notices use clearer wording.

v1.12.8

Cleaner plugin package for review.

Fixed
  • General bug fixes.

v1.12.7

Grok models for every generation mode.

Added
  • xAI is available as a provider for text, images, video, and speech.
  • Grok text models add Grok 4.3 and Grok 4 Fast.
  • Grok Imagine supports image generation, image editing, and a Quality toggle.
  • Grok TTS adds five multilingual voices for speech generation.
Changed
  • Grok Video supports text prompts, first frames, image references, video extension, and 1080p output.
  • Video duration choices adjust to the selected generation mode.
  • Grok Imagine tiers are grouped into one model card.
  • Use a video node as the source for video extension.
Fixed
  • Reference-image generation handles one or multiple images more reliably.
  • Model and mode dropdowns keep their selected text visible.
  • Luma handles larger reference images more reliably.

v1.12.6

More reliable agent text edits.

Fixed
  • Agent text edits keep the rest of your canvas in place.

v1.12.5

Luma images and better generation defaults.

Added
  • Luma Uni-1 is available for text prompts and reference-image generation.
Changed
  • Generated files open in their own tab while your canvas stays visible.
Fixed
  • GPT Image 2 respects landscape, portrait, and square size choices.
  • Luma handles larger reference images more reliably.
  • A prompt with one reference image opens the right image generation mode.

v1.12.4

Friendlier Test button errors.

Fixed
  • The Test button now reports clearer reasons when a key doesn't work.

v1.12.3

Test every provider key in one click.

Added
  • Added a Test button for provider connections.
Fixed
  • General bug fixes.

v1.12.2

English-only for a smoother experience.

Added
  • Launches in English for consistent behaviour across Obsidian builds.
Fixed
  • General bug fixes.

v1.12.1

New nodes always land on empty space.

Changed
  • Generated nodes now auto-place into the nearest free spot.

v1.12.0

Clearer generation status, recoverable placeholders.

Added
  • Live "Generating…" overlay with a running timer on every placeholder.
  • Interrupted generations are flagged when you reopen the canvas.
Changed
  • Placeholder visuals rebuilt for a calmer look.

v1.11.2

Smarter auto-placement on dense canvases.

Changed
  • Generated nodes land closer to the source node.
  • Placeholders match the target aspect ratio from the start.

v1.11.1

More tools for agents.

Added
  • Agents can update many nodes, create groups, and arrange grids in one call.
Fixed
  • General bug fixes.

v1.11.0

Major upgrade for AI agents.

Added
  • Eight new agent tools for tracking jobs, switching canvases, and uploading files.
  • Optional access token to secure the local agent server.
  • A ready-to-use skill package for any compatible agent.

v1.10.0

Split grids, face refs, built-in uploads.

Added
  • Split Grid button turns tiled images into individual nodes.
  • Face references for Seedance videos via BytePlus.
  • Show/hide toggles on every API key field.
  • Pasted canvas images go into a dedicated folder.
  • Built-in file uploads — no cloud setup needed.
Changed
  • Cloud storage settings simplified.
  • Provider descriptions trimmed to one sentence each.

v1.9.2

Polish across settings and pasted images.

Added
  • Show/hide toggles on every API key field.
  • Pasted images land in a Bragi folder, keeping your vault tidy.

v1.9.1

Zero-config uploads, smoother settings.

Added
  • Built-in uploads — no keys required.
  • Rewritten Add Model and Add Provider flows.
Changed
  • Friendlier messages throughout the plugin.

v1.9.0

Rebuilt Providers and Models pages.

Added
  • Add providers and models one at a time — only what you use.

v1.8.1

Friendlier words everywhere.

Changed
  • Notices and dialogs rewritten in plain English.

v1.8.0

One home for every generated file.

Changed
  • Images, videos, and audio all live in one tidy Bragi folder — move or rename canvases freely.
Added
  • One-click migration for upgraders, with an automatic backup.

v1.7.5

TokenRouter and 360° panoramas.

Added
  • TokenRouter — one key for images and text across many models.
  • 360° panorama viewer with mirror and capture.

v1.7.4

Lighter nodes, new card menu.

Added
  • Quick Export and Import for .bragi packages in the card menu.
Changed
  • Refreshed node look — thinner borders, softer shadows.

v1.7.3

Test your storage before using it.

Added
  • A Test button for cloud storage settings.

v1.7.2

A tidier node toolbar.

Added
  • Three-dot menu tucks less-used actions away.
Changed
  • Toolbar reordered for a cleaner look.

v1.7.1

Videos keep generating across restarts.

Added
  • Pending video generations resume automatically after an Obsidian restart.

v1.7.0

Bring your own Cloudflare R2 storage.

Changed
  • Reference uploads use your own cloud bucket.

v1.6.9

Multiple agents can connect at once.

Fixed
  • Parallel agent sessions no longer disconnect each other.

v1.6.8

Finer Seedance duration control.

Changed
  • Pick any duration from 4 s to 15 s, or leave it on Auto.

v1.6.7

Unified image controls.

Changed
  • GPT Image 2 shares the same aspect ratio, size, and quality pickers as Nano Banana Pro.

v1.6.6

Cleaner image size picker.

Changed
  • GPT Image size dropdown shows plain aspect ratios.

v1.6.5

Upgraded to GPT Image 2.

Changed
  • GPT Image 2 with larger output sizes, up to 4K.
  • Slimmer plugin download.

v1.6.4

Pin and Grid polish.

Fixed
  • General bug fixes for Pin and Grid buttons.

v1.6.3

BytePlus support for Seedance.

Added
  • Seedance 2.0 and 2.0 Fast now support BytePlus.

v1.6.2

Pin and Grid buttons.

Added
  • Pin to highlight important nodes.
  • Grid to arrange a multi-selection.

v1.6.1

Internal release polish.

Changed
  • Internal cleanup.

v1.6.0

Audio references and MiniMax.

Added
  • Seedance videos accept an audio reference.
  • MiniMax direct TTS and music, with Chinese voices.

v1.5.2

Agents can trigger generations.

Added
  • Agent tools to list models, inspect upstream, and start a generation.

v1.5.1

Small fixes.

Fixed
  • General bug fixes.

v1.5.0

Upstream text feeds your prompts.

Added
  • Drag to reorder upstream text references — the order becomes the prompt order.

v1.4.0

Claude, GPT-5.4 Pro, and AWS Bedrock.

Added
  • New models: Claude Opus 4.7, Sonnet 4.6, Opus 4.6, and GPT-5.4 Pro.
  • New providers: Anthropic direct and AWS Bedrock.

v1.3.1

Small fixes.

Fixed
  • General bug fixes.

v1.3.0

Text generations can split into many nodes.

Added
  • Ask for N sections and get N connected text nodes.

v1.2.0

Share a canvas as one file.

Added
  • Export and import .bragi packages — graph plus every asset in one bundle.

v1.1.0

First public release.

Added
  • New models: Grok Imagine, Grok Video, Midjourney v8 and niji 7, ElevenLabs direct.
  • Copy+ duplicates a node with every incoming reference intact.
  • Drag to reorder reference images.
  • Face references for Seedance.
  • Download button on every generated asset.
  • Shimmer animation while generating.

For source code and release downloads, visit GitHub (opens in a new tab). Back to home