The Media Gallery
The shared pin-board for images, video, and audio -- used across characters, locations, props, and shots.
The Media Gallery is a shared component that appears on character, location, prop, scene, and shot pages. It's the place where all generated and uploaded media lives, and where you curate what gets used in production.
Think of it as a pin-board: you accumulate media, mark the best items as approved, and archive the rest.
Starring -- marking quality media
Starring marks an item as approved quality -- a "gold star" meaning "you can use this one confidently." Multiple items can be starred.
Starred items float to the top of the gallery in Grid, List, and Graph views, so your best candidates are always easy to find. When you want to use a starred item as an input to a recipe step, drag it from the gallery into the input field -- the star makes it easy to spot among many options.
Starring does not automatically wire an item into a workflow. It is a curation signal, not a selection. Different workflow steps might want different starred items from the same gallery.
Anything can be starred, and the star does not change what the item is. A gallery holds prompts, descriptions, dialogue and audio next to pictures, and a recipe's last output is often its prompt -- so the newest card in a character's gallery may well be text. Star it if it is the good one; nothing stops you.
What that means in practice: anything that goes looking for "this character's approved reference" asks for a picture specifically. If the only thing you have starred is a prompt, a shot that pulls in reference images will pass over it and use your newest image instead, and a readiness row that asks for reference images will still say you need one. Likewise, an input that wants an image refuses anything that is not one -- drag a prompt onto an image slot and you get a message saying so, rather than a job that runs and comes out wrong.
Archiving -- setting media aside
Archiving is the opposite of starring: it pushes an item to the bottom of the gallery, marking it set-aside without removing it. The file stays in the gallery and in storage -- it is a curation signal ("not this one"), not a deletion. Delete is the separate, permanent action for when you want a file gone for good.
Linking media between galleries
A gallery can hold links to items that live in another entity's gallery -- for example, a character's reference image linked into a shot's gallery. This matters because a recipe only takes inputs from the current gallery: you drag an item from the gallery into a step's input slot. Linking brings what a recipe needs into the gallery it runs in, without copying the file.
A link has to name the thing it points back at, so the two galleries that belong to no single entity -- the project-wide gallery and an episode's own gallery -- can be linked into but not out of. Copy or move from those instead.
Unlinking removes the link from this gallery only. The item still exists in its home gallery and in cloud storage -- nothing is deleted. (A character reference unlinked from a shot's gallery is untouched in the character's gallery.)
View modes
The gallery has three view layouts:
| Mode | Use for |
|---|---|
| Graph | Seeing how each item was made -- its ancestry. The richest view, and the one most people work in. |
| Grid | Browsing thumbnails quickly |
| List | Comparing metadata, dates, and tags |
Graph view
The Graph view shows the ancestry of each media asset -- which recipe, workflow step, and input files produced it, tracing back through previous steps in the chain. This is powered by the provenance data that OA stores when it routes a completed ComfyUI job to the gallery (see ComfyUI Integration). Use it to understand how a result was achieved, or to trace which source assets contributed to a final output.
When several outputs came from the same operation run, they share one operation box that fans out to each output -- so a step that produces one track per character, for example, appears as a single box rather than a duplicate per track. Audio items and operation boxes show the time the operation ran along the bottom.
Highlight cues
The same outline cues mean the same thing in Grid, List, and Graph views:
| Cue | Meaning |
|---|---|
| Solid blue outline | The item is selected. Click an item to select it; Shift-click in Graph view adds an item and the files it was built from (that nothing else needs) so you can bulk-archive or delete a dead branch safely. |
| Dashed blue outline | The item you last opened in fullscreen -- a reminder of "what was I just looking at?". It clears when you open a different item or reload, and is independent of selection. |
In Graph view, hovering an item adds extra tracing cues: the hovered item gets a yellow outline, the items that fed into it are marked in blue, and the items it fed into are marked in red, so you can see a node's inputs and outputs at a glance. An item whose right-click menu is open gets an orange outline.
Supported media types
| Type | Formats |
|---|---|
| Images | PNG, JPG, WebP, GIF, SVG, BMP, TIFF |
| Video | MP4, WebM, MOV, AVI, and others |
| Audio | MP3, WAV, AAC, FLAC, M4A, and others |
| 3D Models | GLB |
| Text / References | TXT, MD, external links |
Getting media in
There are four ways to add an existing file to a gallery:
| Route | Use it for |
|---|---|
| Paste | Copy an image anywhere -- a browser, a screenshot tool, another app -- click the gallery and press Ctrl+V (Cmd+V on Mac). The fastest route, and the only one that needs no file on disk. |
| Drag and drop | Drop files from your file manager straight onto the gallery. |
| Upload Files | From the gallery's options menu, the Actions tab, or the empty gallery. Asks where the files are coming from -- this computer, or Google Drive. |
| Paste from Clipboard | The same as pressing Ctrl+V, from the options menu -- use it if your browser blocks the keyboard shortcut. |
Pasting accepts images, video, audio, and text. When you copy an image from a web page the clipboard also carries the page text and the image's address; the gallery takes the picture.
Uploading from Google Drive
Choose From Google Drive at the Upload action and OA opens your Drive. The first time, you sign in with Google and allow read access to your files; after that the same sign-in is reused, including the one you may already have granted for a screenplay document.
You can open folders, search by name, and tick as many files as you like -- ticks are kept as you move between folders, so one trip can collect files from several places. Only files a gallery can hold are listed: images, video, audio and 3D models. Google Docs, Sheets and Slides are not media, so they are not offered.
Each file you tick is fetched and added on its own, keeping the name it had in Drive, and reporting its own progress. If one file cannot be read, you are told which one; the rest still arrive.
Getting media out
Download on an item's "..." menu saves that one file to your computer. It works for images, video and audio alike, and it is on every gallery.
The file is saved under the name the gallery shows for that item -- its description, or the name you gave it, or "Generated by workflow" -- with the original file type kept. Nothing is saved under the long jumble of letters and numbers OA stores files under internally, so a folder of downloads still tells you what each file is.
Generating media
From the gallery, you can trigger AI generation by picking a recipe on the Actions tab. The recipe runs one or more steps and deposits the results back into the gallery. See Recipes & the Cookbook and ComfyUI Integration for how this works.
Suggested actions
The Actions tab opens on Suggested actions -- a ranked short list of what is worth doing next in this gallery, given what it already holds. Every gallery has one, and every gallery leads with something authored for the thing it belongs to:
| Gallery | Leads with |
|---|---|
| Project | Try a text-to-image model, try an image-to-video model -- the workbench for judging a model |
| Episode | An episode score, then an episode title card -- episode-wide artefacts, not shots |
| Scene | A scene storyboard sheet: nine panels on one page, laying the scene out beat by beat |
| Shot | A shot still, then animating it once a still exists |
| Character, Location, Prop | The reference sheet or establishing image that locks the look, then the refinement recipes |
Below the suggestions, More ways to start is always there: AI Models, uploading a file (from this computer or Google Drive), browsing the built-in recipes, crafting your own, and loading one you saved to the Cookbook. The suggestions rank; they never hide anything, and nothing you could reach before is behind them.
A project or episode gallery with no audio in it is also offered a music card, since later sound work assumes a track exists. It ranks above the image-refinement suggestions -- a missing score holds the pipeline up in a way a missing variant does not -- and it goes quiet the moment the gallery holds an audio track.
On an episode the card runs Episode score, which writes its prompt from the episode's musical vision and premise so you start from your own notes rather than a blank field. Trim them down to a few genre, mood and instrument words before you run it -- that is the shape music models read best. On the project gallery you get the plain Generate a music track recipe, for a bed you mean to reuse across the show. Either way the step is a music step, so its model dropdown offers every music model you have enabled, not just the one it starts on.
Working backwards from an image you already have
Generation is not the only direction. If you already have a picture of a character, location or prop -- concept art, a photo, something made elsewhere -- you can put it in that entity's gallery and have the visual properties read off the image instead of typing them in.
Drop the image into the gallery, open the Actions tab, and pick Extract properties from an image. The recipe asks a vision model to describe the picture against that entity's own list of visual properties, and saves the description as a text item in the gallery. You then get proposed values for each property, shown at the top of the entity's Properties page, where you accept or reject them one at a time -- nothing is written without your say-so.
The suggestion appears on character, location and prop galleries once they hold at least one image, and is offered prominently while the entity's visual details are still thin.
You can also run the two halves separately. Any text item in the gallery -- a description you generated, or one you wrote yourself -- offers Review as property proposals on its right-click menu, which turns that text into proposed property values for the entity whose gallery it is in.
Load as Recipe
Selecting Load as Recipe on any gallery item reconstructs a recipe from that item's ancestry -- the same workflow steps, input configuration, and connections that produced this result. You can then:
- Save it to the Cookbook as a new recipe for future reuse
- Upvote an existing recipe if an identical one is already in the Cookbook
This is the natural way to build the Cookbook: generate something good interactively, then capture how you did it so it can be repeated.
Image editing
The gallery includes a built-in image editor with:
- Rectangular, spherical, and cylindrical crop
- Perspective and 3D pose tools (OpenPose SVG)
- Colour adjustment and layering
- Sketch mode
Tags
Items can be tagged for filtering and workflow targeting. Tags support suggestions and can carry purpose hints (first, last) used when ordering items within a generation sequence.
A tag names a set. That is different from a star, which means "approved". An item can carry any number of tags, and a tag implies nothing about quality. Tagging also never hides anything -- the gallery is a scratchpad, and an untagged item stays exactly as visible as a tagged one.
Tagging several items at once
You can name a set in one go. Select the items you want -- click one, then Ctrl-click (Cmd-click on a Mac) to add others, or Shift-click to take a run of them -- then open the gallery's More options menu and choose Add Tag. Type any word you like and it is applied to everything selected. Remove Tag works the same way in reverse, and takes away only the tag you name; the item's other tags, including the ones OA fills in automatically such as media type, dimensions, and duration, are left alone.
Tags match without regard to capitals, so an item never ends up with the same tag twice.
This is the fastest way to hand a chosen set to the assistant: generate ten images, look at them, tag the five good ones, and then talk about that tag by name.
Selecting a step output
When a recipe has multiple steps, the output of one step can be the input to a later step. Clicking on a completed output in the gallery selects it -- a checkmark appears -- and all later recipe steps that are linked to that output automatically refresh their inputs to reflect your selection.
This lets you experiment: run step 1 multiple times to get several candidates, click the one you want, and steps 2, 3, and any other linked later steps update instantly to use that output as their starting point.
You can manually override a later step's input by dragging a different item into its input slot. That step no longer follows the selection from the earlier output. To restore the link, click the earlier output again and the override is reset.
Shot-to-shot chaining
The same selection mechanism works across shots. The output of a step in one shot can feed as an input to a step in a later shot -- not just the immediately following shot, but any later shot that references it.
How it works:
- Run a recipe step in one shot and click its output to select it
- In a later shot's recipe, the input field for a linked step is pre-filled with that selected output
- The graph view shows these cross-shot connections explicitly
Starred items from the earlier shot's gallery make it easy to find your best candidates -- but you drag the one you want into the input field rather than having it wired automatically.
Upstream suggestions
When you open the recipe panel, input fields may be pre-filled with suggestions based on what was previously selected in earlier steps within this gallery session. These suggestions are persisted so they survive page reloads. You can always override a suggestion by dragging a different item in, and reset it by clicking the original output again.
Provenance
Every gallery item generated through a ComfyUI workflow carries provenance: the recipe that produced it, the step within that recipe, the input files used, and the workflow JSON. This is what powers the Graph view and the Load as Recipe feature. Provenance is stored when OA detects a completed job and routes its output to the gallery.
Where it appears
The same Media Gallery component is used on:
- Projects -- the project-wide workbench, for trying a model or workflow when the result belongs to no single entity
- Characters -- character visual references and generated images
- Locations -- location reference imagery and generated backgrounds
- Props -- prop visual references
- Episodes -- media that belongs to the whole episode, such as a music bed
- Scenes -- scene-level media
- Shots -- shot-level generated media (the primary output of The Shoot)