TapNow changelog
See the latest TapNow features, important changes, fixes, and announcements.
v2.18.13
Start creating with Astra 6 Studio
Open Astra 6 Studio in the App Store to choose a play by creative direction, such as 3D previs, motion design, depth filmmaking, or fashion. Review each play's inputs, outputs, and limits, then start from an example or try it in a conversation.
Learn how to use Apps →Seedance 2.5 Draft Mode
Seedance 2.5 video nodes now include Draft Mode: preview actions, composition, and references at 480P, then select Generate Final Video to reuse the draft's prompt and references for a 1080P result. Draft revisions and final generations stay as separate canvas nodes.
Learn how to generate video →Retake shots with Depth Filmmaking Studio
In Depth Filmmaking Studio, add a source motion video and references for the character, setting, wardrobe, or props. TapNow creates a reusable depth motion first, then retakes the shot using your references. The result appears as a new canvas node while the source video stays available.
Learn how to use Apps →v2.17.0
Collect canvas nodes into a pile
Select two or more image, video, audio, or text nodes on the canvas and choose Stack in the selection Toolbar. They collapse into one pile that takes the space of a single node. Select the pile to see everything inside, and drag a node back onto the canvas to use it on its own. A pile holds up to 50 nodes, and deleting a pile also deletes the nodes inside it.
Learn how to stack nodes →Choose how batch results are arranged
Open Canvas Settings and set Batch generation results to Pile or Spread to control how several results from one run land on the canvas. The setting applies to later runs only; nodes already on the canvas are not rearranged.
Learn how to stack nodes →Generating again no longer overwrites the previous result
When you generate again on an image, video, or text node that already has a result, that result stays on the canvas and the new one lands in a newly created node, arranged according to Batch generation results. The new node keeps the input connections of the original and is set to generate once, so you can compare attempts side by side. Audio nodes still update in place.
Learn how to stack nodes →v2.16.1
Film & Video Previsualization is in the App Store
Open Film & Video Previsualization in Apps to break a script into previewable shots, action, pacing, and transitions before a shoot. Open the item and select Try in Chat to place its example Prompt in Agent, or select Add to Chat and then supply your own script or scene text, target duration and shot count, and reference images or footage. The more complete the script, the closer the shot plan stays to the real shoot.
Learn how to use Apps →v2.15.14
Add an image reference to Seed audio 1.0
After selecting Seed audio 1.0 in an audio node, add one JPG, PNG, or WebP image up to 10 MB in the reference row, or add up to three reference audio clips. You cannot use image and audio references together. Check the page warning and estimated spend before generating.
Learn how to generate audio →v2.15.11
Explore use cases in the Creative OS App Store
Open Apps in the sidebar and browse Apps, Official Skills, or a specific use case. The catalog includes Whitebox Video Previs, Image to 3D Modeling, Design Room, Casting Room, and Film & Video Previsualization. Open an item and select Try in Chat to place its Prompt in Agent, or select Add to Chat before adding your own references and constraints.
Learn how to use Apps →v2.15.10
Follow Agent task progress and history
During a longer Agent task, the conversation shows the current steps and progress. After it finishes, expand task history to review completed actions and results. You can continue in the same conversation or use the history to check what happened.
Learn how to use Agent conversations →v2.15.3
Show new badges on TapTV creator profiles
Open a TapTV creator profile to see localized identity badges such as Visual Ambassador, TapTV Signed Studio, TapNow Quality Creator, and Pioneer Creator. The badges also appear in creator identity information; The badges shown can vary by creator profile.
See the TapTV tutorial →v2.15.0
Download canvas media in batches
Select multiple image, video, or audio nodes on the canvas and click Batch download in the selection toolbar. Creative OS packages the available source files and downloads them; text, empty, and still-generating nodes are skipped.
Learn how to download in batches →v2.13.33
Generate faster with MiniMax H3 Max
MiniMax H3 Max is the high-speed option in the H3 family, built for quick drafts and rapid iteration. It supports text-to-video and image-to-video, producing 5–15 second videos at 480P or 768P with native audio. Select it from a video generation node or an Agent confirmation card.
Learn how to generate video →v2.13.23
Let Agent organize an authorized folder
In TapNow Desktop, authorize a local folder and tell Agent which subfolders to create or which files to move or rename. Agent shows the full set of actions for approval, works only inside that folder, and rolls back completed changes if any action fails.
Learn how to work with Agent →v2.13.18
Start from an App example
Open an App to view image or video examples and insert a sample instruction into the Agent input. When you add an App from the + menu, you can also select the suggested example and adapt it to your task.
Learn how to use Apps →Set Agent's thinking level
Before starting a new conversation, open the model menu to review model details and choose Off, Light, Standard, or Heavy when the model supports it. The model locks after your first message, but you can still adjust its thinking level from the adjacent control.
Learn how to work with Agent →Review audio settings before generation
When Agent prepares audio in Ask mode, use the confirmation card to review or change the model, duration, voice, and other settings supported by that model. The model runs and uses Tapies only after you select Generate; the result appears on the canvas.
Learn how generation modes work →v2.13.17
Download TapNow Desktop for Windows
Open the TapNow global download page on a 64-bit Windows computer and select Download for Windows. The Apple silicon build remains available for macOS. TapNow Desktop is not yet available in the China region.
Read the download and update guide →Ask Agent to explain a shared canvas
Open a read-only canvas share page on desktop and select Explain How It’s Made. TapNow clones the canvas, opens an editable copy, and asks Agent to explain the nodes and connections. The original stays unchanged. You must sign in, the action is estimated to use 40–150 Tapies, and the option is not shown on mobile.
Learn how sharing and cloning work →v2.13.16
Check for TapNow Desktop updates manually
In an installed TapNow Desktop app, open Settings and select Check for updates. TapNow checks for and downloads available updates. When the update is ready, follow the prompt to select Update now or Restart and update. Make sure the current canvas is saved first.
Read the download and update guide →v2.13.15
Generate video with Wan 3.0
Select Wan 3.0 in a video generation node to create a video with audio from text, a first frame, or 1–10 reference images. It supports 480P, 720P, 1080P, and durations from 2–30 seconds or Auto. Model availability depends on your account.
See the video generation tutorial →v2.13.14
Authorize an App directly in Agent
When a task needs an external service, Agent shows an authorization action in the conversation. Complete authorization, return to the same conversation, and continue the original task.
See the Apps tutorial →v2.13.12
Sign in to an enterprise team with SSO
Members of configured enterprise teams can select Continue with SSO on the sign-in page, enter their company domain, and complete their organization’s sign-in. SSO and personal accounts remain separate, and the entry appears only for configured enterprises.
See the teams and permissions tutorial →Switch and rename canvases more directly
Inside a canvas, select the arrow beside its name to search, switch, or create a canvas. Select the canvas name to rename it directly, or select the TapNow logo to return to the canvas home page.
See the canvas management tutorial →v2.13.11
Reference more canvas content in Agent
Type @ in the Agent input to add canvas nodes, library assets, Elements, and folders to a task. Review the references before sending and remove anything the task does not need.
See the Agent conversation tutorial →Clearer node markers
Node marker actions and selected states are easier to recognize, so you can quickly confirm which nodes are marked on a busy canvas.
v2.13.9
Smoother canvas sharing and cloning
Opening and cloning a canvas from a shared link is smoother and more reliable when you continue working from someone else’s content.
v2.13.8
Use the full canvas on a tablet
Open the full canvas on iPad and Android tablets to review nodes, chat with Agent, and continue creating. Phones still use the small-screen access experience.
See the canvas introduction →v2.13.7
Add library content more directly
Select an image, video, or audio asset to add it to the canvas. Select a folder to expand or collapse it, and select an Element to open its editor. Preview remains available when you want to inspect an asset before applying it.
See the library tutorial →v2.13.6
Improved Agent web search
Agent web search feels smoother overall when you look for public information, facts, and creative references.
v2.13.5
Smoother browsing and sign-in
Opening Creative OS, browsing pages, and signing in now feel smoother and more consistent.
v2.13.4
See estimated Tapies before running a group
After you choose Run Group for a group of nodes, the confirmation window attempts to show the estimated Tapies. You can confirm or cancel. Final usage is based on the completed task.
See the node group tutorial →Improved Agent results
Agent delivers more consistent creative task results, with smoother task continuity and result presentation.
v2.13.3
Seedance 2.5 now supports 1080p
When you use Seedance 2.5 to generate a video on the canvas, open Resolution and select 1080p. Frames, Omni Reference, and Video Edit all support this option. New tasks still start at 720p.
See the video generation tutorial →v2.13.1
Answer several Agent questions at once
When Agent needs more than one piece of information, its questions appear above the input. You can answer up to four questions one by one and submit them together. The answer summary remains available in the conversation.
See the Agent conversation tutorial →v2.12.29
Preview 3D content before opening a studio
Open a 3D asset, panorama, or 3D scene to rotate the object or look around first. Select Open Viewfinder, then Capture, to add the photo directly to the canvas. When you want to continue building the scene, select Use in 3D Studio.
See the 3D tutorial →Use Library elements as MiniMax H3 references
Choose MiniMax H3 in Reference mode, then select Add element to use a visual reference from the Library. This option is not available in Multi-Shot mode. You can use up to nine images, three videos, and three audio clips at a time. Audio must be used with at least one image or video.
See how to use elements →v2.12.28
Ask Agent to explain how a TapTV project was made
Open a TapTV project preview on desktop and select Explain How It’s Made. TapNow clones the project, opens an editable canvas, and asks Agent to explain the creative approach through its nodes and connections. The original public project remains unchanged. You need to sign in, the action is estimated to use 40–150 Tapies, and it is not currently available on mobile.
See the TapTV tutorial →v2.12.19
Extend a video and retake individual segments
Select a video node and use Continue video · Beta to add 4–30 seconds before or after it. You can also use Video Retake to set a new view, shot scale, or camera move for each time segment. Both tools are in Beta. The result appears as a connected new node, while the source video stays on the canvas.
See the video editing tutorial →v2.12.18
Generate with Seedance 2.5 on the canvas or in Agent
Choose Seedance 2.5 in a video node or an Agent confirmation card, then set the mode, references, a 4–30 second duration, and output settings to generate the result on the canvas. Reference mode accepts up to 30 images, 10 videos, and 10 audio clips. Model availability depends on the options shown for your account.
See the Seedance 2.5 tutorial →MiniMax H3 adds 768P, four-second video, and nine reference images
Choose MiniMax H3 in a video node to set Resolution to 768P or 2K, choose a duration from 4 to 15 seconds, and add up to nine images in Reference mode. New tasks still start at 2K and five seconds. Check the updated Tapies estimate before generating.
See the MiniMax H3 tutorial →v2.12.13
Generate audio with Seed audio 1.0 and references
Choose Seed audio 1.0 in an audio node, enter a prompt, and add up to three audio references before setting the format, subtitles, and advanced controls. The result appears as a playable waveform. When subtitles are enabled, a connected audio-subtitle text node is also created. Image references are not currently supported.
See the audio generation tutorial →v2.12.10
Search History and return multiple results to the canvas
Open History from the left side of the canvas to search generated images, videos, audio, and 3D content, or switch between All projects and This project. Choose Select to apply or download several items at once. History stores generated results, not a snapshot of the entire canvas.
See the History tutorial →v2.12.9
Generate video with MiniMax H3
Choose MiniMax H3 in a video node to generate video with native audio through Frames or Reference. At launch, it supported 2K, 5–15 seconds, and up to five reference images. See the later version above for its expanded settings.
See the MiniMax H3 tutorial →v2.12.5
Reuse people, products, and characters with Elements
Open Library and Elements from the left side of the canvas to create an element from canvas content or a local file, then save it to your Private or Team space. In a supported model’s Reference mode, use Add element or @ to reuse the same person, product, or character.