Image Studio (native panel — generate, compare, library, stats, templates, post-processing)
An image studio built into Omniscio: write a prompt and generate, compare several models on the same prompt, browse and search your whole generation history, watch what you have spent, save reusable templates, collect images into named galleries you order by hand, and post-process finished images. All in one panel, no browser.
On this page
What it is
A first-class, in-app image studio built natively into Omniscio. You generate AI images from a prompt, compare several models on the same prompt side-by-side, browse and search your whole generation history, watch your spend, save reusable prompt templates, gather images into named galleries you order by hand, and post-process finished images (AI upscale and background removal) — all inside one panel, without opening a browser.
Three things share the "Image Studio" name — this page covers only the first. Don't confuse them:
- Image Studio (native panel) — this page. A native four-tab panel in the Omniscio sidebar, described below.
- Image Studio MCP — a set of agent tools for Claude CLI sessions (generate, compare, browse, templates, and shareable links). See jls-image-studio.md. This is where share links live.
- Image Studio (embedded website) — the older sidebar panel that embedded the live
jls-image-studio.web.appsite in a webview. The native panel on this page replaces it. See jls-image-studio-app.md.
Where to find it
Status — off until you switch it on
The native panel is off by default. The Enable Image Studio switch in Settings →
Built-in Apps (also Image Studio in the sidebar item picker) adds an Image Studio
row to the projects sidebar, and that row opens this native panel — not the website. Until
the switch is on, no "Image Studio" entry appears in the sidebar. The app's own feature list
(Settings → Lab) still marks the panel in development as image-studio-native, but that
entry is only a label: nothing in the app reads it to show or hide the panel.
With the switch on, an Image Studio row appears in the projects sidebar (a pink image icon). Opening it gives the panel the whole content area — a top tab bar with four tabs: Studio, Library, My Stats, and Templates — plus a full-screen image viewer that opens over any image.
Two more things to know up front:
- Desktop only. Every operation is refused over the mobile / Web Access bridge — there is no phone surface yet.
- Sign-in required. Generating, listing, post-processing, and templates all need you to be signed in to your Omniscio account. Signed out, the panel asks you to sign in first.
The Studio tab — generate images
The Studio tab is a two-pane surface: the generation form on the left, the results grid on the right.
The form reads top to bottom in the order you decide things (redesigned 2026-10-11): Prompt (Subject, Style) → Model → Output (size, ratio, how many, transparent background) → References → File (filename base). The one loud control is the banana Generate button pinned at the bottom, and it carries the price of what it is about to do.
Visual design — the website layout, but theme-following. The Studio keeps the website's layout (prompt prominent at the top, a compact multi-select model picker, a banana-gradient Generate button), but its surfaces now follow the app's light/dark theme — light in light mode, dark in dark mode — instead of the original always-dark island. This is done centrally: the JLS-only
dark-*colour scale intailwind.config.jsaliases the theme surface vars (--color-surface-*), so everybg-dark-*/border-dark-*adapts at once, and text uses the surface tokens. What stays FIXED regardless of theme: thebananabrand accent (a yellow-gold ramp; on-accent text is dark —text-zinc-950— in both modes), and the fullscreen image viewer +bg-blackimage scrims (a media backdrop stays dark so photos read and its glass controls survive — the viewer roots a forced-darksubtree). Thebanana+darkscales live intailwind.config.js.
Writing the prompt
- Subject (required) — describe what to generate. It is the tallest box on the form, and on a blank session the cursor starts in it. (With results already on screen it does not grab the cursor, so the tile shortcuts C/D/R/X keep working when you come back to the tab.)
- The Subject's toolbar sits right under the box: Recent (your last prompts), Save template, and Clear (when there's text). The ⓘ beside the label explains multi-prompt.
- Style (optional) — art direction, e.g. "photorealistic, oil painting, neon."
- Multi-prompt. The Subject box can hold several prompts at once. Separate them
with a blank line or a line containing only
---. Each prompt then generates its own batch of images, and a "N PROMPTS" badge appears in the toolbar under the box so you can see how many were detected. - Character limit. Each model has a maximum prompt length. The counter stays hidden until your longest prompt reaches 90% of it, then appears in amber; going over turns it red and blocks Generate. In comparison mode the strictest selected model sets the limit.
Choosing a model
The model control is a compact multi-select dropdown on its own full-width row, right after the prompt (its trigger shows the selected model and a one-line hint). Open it and pick one model for a normal generation, or two or more to enter multi-model comparison mode; each option is a checkbox row with the model name and a capability hint on hover. It lists 9 models.
| Model | Provider | Sizes | Reference images | Prompt limit | Est. price / image |
|---|---|---|---|---|---|
| NB2 Lite (default — cheapest) | Google Gemini | 1K | up to 14 | 32,000 | ~$0.039 |
| Flash (fastest) | Google Gemini | 1K | up to 14 | 32,000 | ~$0.039 |
| NB2 (only model that does 0.5K) | Google Gemini | 0.5K / 1K / 2K / 4K | up to 14 | 32,000 | ~$0.077–0.151 |
| NB2.1 (newest Nano Banana — cheaper than NB2 at every size) | Google Gemini | 1K / 2K / 4K | up to 14 | 32,000 | ~$0.039–0.076 |
| Pro (highest Gemini quality) | Google Gemini | 1K / 2K / 4K | up to 14 | 32,000 | ~$0.155–0.24 |
| SeedDream 4.5 | Replicate | 1K / 2K / 4K | up to 10 | 4,000 | ~$0.06 |
| Ideogram 3 (strong text) | Replicate | 1K | up to 3 style refs | 4,000 | ~$0.06 |
| GPT Image 2 (best text) | OpenAI | 1K / 2K | up to 14 | 32,000 | ~$0.211 (1K) / ~$0.844 (2K) |
| GPT Image 1.5 (the only see-through one) | OpenAI | 1K | up to 14 | 32,000 | ~$0.133 |
Prices are pre-generation estimates and depend on the size you pick; the charged amount comes from the server.
This list mirrors the JLS app — JLS is upstream and wins. It was 13 models until
2026-09-01, when six ids JLS had retired (seedream-5-pro, seedream-5-lite, the three
ideogram-v4 tiers, muse-image) were removed: the picker was offering models the server
could no longer generate. gpt-image-1.5 was added in the same pass. If this table and the
JLS app disagree, re-derive from JLS, never the other way round.
GPT Image 2 at 2K really is 4× its 1K price, not cheaper. The estimate said ~$0.165 for a long time — OpenAI's 1024-class price mistaken for a size tier — which made the bigger render look cheaper and under-reported spend ~5×. Do not "restore" that ordering.
Size and aspect ratio
- Size — one of 0.5K, 1K, 2K, 4K, restricted to what the chosen model supports (only NB2 offers 0.5K). A model with a single fixed size locks the selector and says "Fixed for this model."
- Aspect ratio — Auto (matches the first reference image, or 1:1 if there is none), or one of 1:1, 4:3, 3:4, 16:9, 9:16.
Transparent background
A Transparent background switch sits under the size row. Turn it on and the image is generated with a real see-through background (a true alpha channel) instead of a solid one — useful for logos, icons, stickers and anything you want to drop onto another design.
- It only appears for GPT Image 1.5, because that is the only model that can do it. The control is hidden — not greyed out — for every other model.
- It is not an OpenAI-wide capability. GPT Image 2 is also an OpenAI model and still cannot do it; the server refuses the whole request rather than quietly returning a solid background, which is why the control is genuinely locked rather than merely discouraged.
- Switching to a model that can't do it turns the switch off and tells you so, so it can never sit silently on behind a hidden control and surprise your next generation.
- In a comparison, the setting rides only on the GPT Image 1.5 request. The other models in the comparison are unaffected and still succeed.
- It costs the same as a normal image, and it works alongside reference images.
- A transparent result is drawn on a checkerboard in the results grid and the viewer, so you can see at a glance that it worked — the same treatment a background-removed image gets. Downloading keeps the transparency.
Related but different: Remove background (in the post-processing menu) takes an image you already generated and cuts the background out afterwards. This switch asks the model to render it see-through in the first place — one paid call instead of two, and a real alpha channel rather than an approximate cutout.
How many, and what it costs
- A one-click row of numbers sets the count, 1–10 (default 2; 1–3 per model in comparison mode). You can also press Shift + 1…0 to set it directly — whenever the cursor is not in a text box (there, Shift + a number types a symbol as usual).
- The Generate button shows the live estimated cost of the whole batch, e.g. "Generate 4 Images · ≈ $0.16".
- Asking for 20 or more images total pops a confirmation first, so a big spend is never one accidental click.
Reference images
Some models accept reference images to steer the result. The form shows two drop zones — one for content references and one for style references. Add images by dragging, clicking to browse, or pasting.
- Combined cap: 14 across both zones. 20 MB per file. Accepted formats: PNG, JPEG, WebP, GIF.
- How many each model uses varies: the Gemini models and both GPT Image models take up to 14; SeedDream 4.5 up to 10; Ideogram 3 up to 3 style references. Every model currently offered accepts at least one reference image.
- GPT Image 2 used to take only the first reference — that changed when OpenAI's multi-image edit path landed upstream, and it now uses up to the same combined cap of 14.
- In comparison mode, references are only available when every selected model supports them; otherwise one short note replaces both zones and says why.
Generate, and cancel
- The button reads "Generate N Images · ≈ $X" (or "Compare N Models · ≈ $X" in comparison mode). Ctrl + Enter (⌘ + Enter on Mac) also fires it — the key is drawn on the button on wide windows and in its tooltip.
- While a batch runs, the button becomes Cancel. Cancelling stops waiting on the batch — but any image already paid for and in flight still finishes and lands in your Library (a cancel can't refund work already running).
- A slow model (Pro, GPT Image 2) can take a few minutes. The panel keeps waiting as long as the app does, so a slow image is no longer reported as "failed" at two minutes while it is still being made and charged.
The results grid
Finished images appear on the right under a "This session · N images" heading, newest batch first, each with a model badge and a cost badge. An image still being made shows a spinner and "Generating image…". A see-through image sits on a checkerboard instead of the usual solid tile, so you can tell it worked without opening or downloading it. Hover an image (or focus it) for quick actions:
| Action | Shortcut |
|---|---|
| Open in the full-screen viewer | click / Enter |
| Copy to clipboard | C |
| Download | D |
| Use as a reference (sends it back to the form) | R |
| Remix (reopens the form with this image's settings) | X |
An image that failed shows a non-hanging error tile instead of spinning forever, and the pop-up names the real reason (for example, out of credit). Clear failed (N) beside the "This session" heading removes every failed tile at once. Before you've generated anything, the grid shows "No images yet" with four example prompts. Clicking one only fills the Subject box — nothing is generated or spent until you press Generate.
Handy extras
- Recent prompts — a clock popover (in the toolbar under the Subject) with your last 20 prompts; click one to restore its settings.
- Session stats — the $ amount in the panel header, next to the key icon (desktop only). Click it for a popover tallying this session's images, spend, and per-model breakdown (using real server costs).
- Save as Template — save the current subject, style, and reference images for reuse (see the Templates tab).
How it behaves
Billing — read this before you generate
Generating images and post-processing them spend prepaid gateway AI credit (the same balance you top up under Settings → Accounts & AI → Plan & Usage; see stripe-credit-topups.md). A few rules make the spend predictable:
- The price you see before generating is an estimate. The "≈ $X" on the Generate button is computed locally from a price table. The amount you are actually charged is whatever the server returns with each finished image — never the estimate.
- You only pay for images that arrive. If a requested image fails to generate, it is not billed; you get a small error tile that says so ("you weren't charged for it").
- Out of credit is a clear message. If your balance can't cover a request, the panel tells you to top up and try again, rather than showing a raw error.
The whole money path lives in the Omniscio gateway, not in the app — the app only
displays what the server reports. (Wiring: unified-image-gen-billing-contract.)
Multi-model comparison
Select 2 to 8 models and the Studio switches to comparison mode: the same prompt(s) run across every selected model so you can judge them side by side.
- Each model generates 1–3 images (the "images per model" slider; default 1).
- Results are grouped into a "Model Comparison" block per prompt, organized by model, so you compare like with like.
- The size offered is the shared ceiling all selected models can honor, and — as above — reference images require every selected model to support them.
The Library tab — your whole history
Every image you generate (and every post-processed result) is saved to your account and shows up here.
- Grid with infinite scroll, ~20 images per page — scroll to load more.
- Search by prompt text — case-insensitive, debounced as you type, over your most recent 500 images (a note tells you when you've hit that window).
- Filters — a model dropdown, date presets (Today / This Week / This Month / All), and a custom date range.
- Comparison sets are grouped back together as "Model Comparison" blocks.
- Bulk actions — click Select (or press Ctrl + A) to multi-select, then Delete (with confirmation) or Download ZIP (up to 500 images at once).
- Per-image — hover (or focus) a tile for copy (C), download (D), use as reference (R), remix (X) and add to a collection; delete sits apart at the right. Each button's tooltip shows its key. A delete is optimistic and offers Undo.
- Badges — each tile's model and cost badges appear on hover; on a touch screen they stay visible.
- Look (redesigned 2026-10-11) — a plain Library header with the image count, search and
the model / date filters on one row, flat comparison groups, and the shared page column every
Image Studio tab now uses. The layout follows the app light/dark theme; image thumbnails keep a
dark mat and the
bananaaccent marks only selection. - Errors — if the Library can't load, it says so with a Retry button; a search or filter that matches nothing offers Clear filters.
The full-screen viewer
Clicking any image opens a full-screen viewer:
- Zoom with the scroll wheel (up to 20×, toward the cursor); double-click or press 0 to reset. Pan by dragging when zoomed.
- Navigate with the on-screen arrows, the ← / → keys, or a swipe on touch; an index pill shows "N / total."
- Actions — a direct Download button (D) leads the toolbar, then Copy (C); then a Refs menu (add as reference A, set as reference R, remix X), Markup (M) and the Edits toggle; then the AI menu (upscale / remove background); then Share. When an image has markup, an Export menu also offers Download with edits.
- Saving markup — Save keeps the editor open and Save & Exit (or Ctrl + Enter) closes it, but only once the markup has actually been saved: the button shows it is working until then, and "Markup saved" appears after the save lands. If the save fails, the editor stays open with the reason at the top so you can try again; Cancel then Discard leaves without saving.
- Shortcuts — the ? button in the top bar (or the ? key) opens a list of every shortcut; Esc closes that list first, and a second Esc closes the viewer.
- Prompt — shown beneath the image (Shift + P copies it); a long prompt scrolls inside its own box instead of pushing the image off screen.
- If an image fails to load the viewer says Image unavailable instead of showing a blank frame. A background-removed image is shown over a transparency checkerboard.
Post-processing (the AI menu)
From the viewer's AI menu you can transform a finished image:
- Upscale — 2× or 4× (Topaz).
- Remove background — via BRIA or 851-labs, producing a transparent PNG.
Each of these creates a new image (it never overwrites the original). The new image is billed on the cost the server returns, is inserted right after its source in the viewer, and is added to your session and your Library. These operations are slow (up to about 1–2.5 minutes) and are never retried automatically (a re-run would bill again). If the server can't produce a result, you get an honest message about whether you were charged.
The My Stats tab
An account-wide summary of your usage:
- Totals strip — total images, total spend, and prompts run, in one quiet row.
- Per-model breakdown — each model you've used, with its image count, spend, and a proportional bar (long model names are shortened rather than overlapping the numbers).
- Highlights — your favorite (most-used) model, your priciest single image, and the month you started creating.
There are no filters or date ranges here — it's your all-time total. Before you've generated anything it shows a "No stats yet" empty state with a Go to Studio button, and if the stats can't load it shows the error with a Retry button.
The Templates tab
A template is a reusable starting point for the form.
Visual design. The Templates tab uses the shared Image Studio page header and column, a card grid with each card's Load / edit / delete buttons in a footer row (so long names are not cut off), an inline name/subject/style edit card, and the island's theme-following banana palette (
banana/darkscales intailwind.config.js).
- What it stores — a name (up to 60 characters), the subject, the style, and any reference images (content and style). It deliberately does not store the model, size, or aspect ratio, so a template stays flexible across models.
- Saving — from the Studio, fill in a subject and/or style and click Save as Template. The dialog summarises what will be saved (e.g. "1 reference image · model & size are not saved"). You can keep up to 50 templates; at the limit the dialog says so before you type a name.
- Managing — the Templates tab lists your templates as cards. Load fills the form with a template's subject, style, and references; you can also edit or delete a template inline. Templates are stored on your account (server-side).
The Galleries tab — named, ordered collections
A gallery is a named, hand-ordered set of your images that lives on your account. Where the Library is your whole history in one stream, a gallery is a folder you curate — "Client pitch", "Blue-hour refs" — and it keeps the order you put the images in.
Desktop only. Every gallery operation is refused over the mobile / Web Access bridge (there is no mobile gallery UI yet), so the tab does not appear in a browser session.
- Make one — click New gallery in the Galleries header, type a name and Create (Esc cancels). Rename it later by clicking the name; Delete on the card removes it after a confirm step — your images are not deleted, only the gallery.
- Put images in it — two ways, on the same Add Images screen. From History (the default) picks from images you have already generated; Upload takes files from your computer by click or drag-and-drop (PNG, JPEG, WebP, GIF, 20 MB per file, several at once). A file over the limit is skipped by name and the rest still upload. A brand-new gallery shows "This gallery is empty" with Upload images and From history buttons.
- Order them by hand — drag a tile to reorder. The new order saves immediately, and reverts on the spot if the save fails.
- The cover picture is the first image. There is no "set as cover" control — the cover is whichever image the gallery lists first, so reordering is how you change it.
- Rename or remove one image — from the tile's pencil and ✕ buttons (both reachable from the keyboard). Removing takes it out of the gallery only; the original stays in your Library.
- Copy between galleries — click Select, pick images ("N selected"), then Copy to Gallery to drop the same images into another one.
- Errors — if the gallery list, a gallery, or your history can't load, the screen says so with a Retry button instead of showing an empty list.
Galleries are free — every gallery route is organizational CRUD and none of them generate an image, so nothing here costs credit.
Sharing & collections
The native panel has an in-panel Sharing surface — a pixel-for-pixel port of the JLS website's sharing UI, rendered as a fixed dark "banana" island (theme-independent, matching the website rather than the app theme). Desktop-only for now. Three surfaces:
- Share one image — a Share button in the
ImageVieweropensShareModal: pick an expiry (1 day / 7 days / 30 days / never) and copy the public link. - Share several as a collection — multi-select in the Library, then Share in the
bulk bar opens
BulkShareModal: name the collection and get one public link. - Manage everything — Manage shares in the Library header opens
ShareManager, a full-screen island with two tabs: Links (every share link, with view count + expiry; copy or revoke each) and Collections (delete a collection — the images are untouched).
A share link is a PUBLIC capability URL (jls-image-studio.web.app/share/<token>) — anyone
with the link can view; the UI says so and lets you revoke anytime. It all flows through the
Omniscio gateway (/v1/jls/{shares,collections}) under your signed-in account — never
Firebase. Sharing is FREE (no spend); create / revoke / delete are desktop-only and blocked
on the mobile/web bridge. A multi-image collection share is two chained calls (create the
collection, then share it) — the REST API has no combined route.
Related surfaces under the Image Studio name: the Image Studio MCP integration
(jls-image-studio.md) exposes the same capability to agents
(create_share / list_shares / revoke_share); the standalone JLS Image Studio web app
(jls-image-studio-app.md) is a separate product.
The Collections tab
A collection groups images so they can be shared together with one link. The tab lists your collections as cards (name, "N images · date") under the shared page header, with New collection as the one main button. Each card can be shared, renamed (Enter saves, Esc cancels, an empty name is refused with a message) or deleted. You can keep up to 50; the count appears near the limit and the button explains when it is reached. From any image, Add to collection opens a small dialog listing your collections — it always reloads the list when it opens and shows Retry if that fails, so it never adds to an out-of-date list.
The API key screen
The key icon at the right of the Image Studio header opens one card, Connect your API key: paste your JLS Image Studio key and Save key. The key is never shown again (only that one is saved, with Replace and Remove), and a link opens the website to get or manage keys. If a save fails, the key you typed stays in the box so you can retry without re-pasting it.
The Storyboard tab — a script, scene by scene
Still in development, behind its own flag. Paste a script, pick an AI model and press Analyze Script (a small paid AI step) to break it into scenes; each scene gets a card with its description, location, mood, characters and camera ideas.
- Reference photos — the paperclip on a scene card attaches photos (actors, wardrobe, locations) that are sent with that frame's image request. They are saved with the storyboard and are still there when you reopen it. A photo too large to save shows a message and is not attached.
- The price is on the button — Generate, Regenerate and Retry each show the estimated cost of one frame for the image model picked above the scenes (for example "Generate · ≈ $0.039"), and the number follows that picker. Frames are made at the 1K size the price is quoted for.
- It asks before it spends — clicking opens "Generate this frame?" with the price and model. Cancel (the pre-selected button) buys nothing and changes nothing.
- A failed save is never silent — if the storyboard can't record that a frame started, nothing is bought; if it can't link a finished, paid image to its scene, the image stays on screen and a message offers Save again.
- Interrupted frames — a scene left mid-generation (the app closed, or a save failed) shows Interrupted with a priced Retry instead of staying stuck on "Generating…".
- Leaving mid-generation — Back asks "Leave storyboard?" while a frame is being made. Leaving does not stop that frame: it finishes, is charged, and is saved to its scene.
- Export and share — the Export menu downloads a PDF or the scene images, or publishes a share link.
Known limitations
- Desktop only — no mobile / Web Access surface yet.
- Requires sign-in and prepaid credit — generating and post-processing spend real credit; running out prompts a top-up.
- Post-processing is slow and never auto-retries — upscale / remove-background can take a minute or two, and each run bills.
- Sharing is desktop-only — the Share / bulk-share / Manage-shares surfaces are hidden on the mobile/web bridge (the share IPC is desktop-only); a paired phone has no sharing UI yet.
- Estimates are approximate — the estimate on the Generate button is a guide; the charged amount is whatever the server returns.
Related
- jls-image-studio.md — the Image Studio MCP server (agent image tools and shareable links).
- jls-image-studio-app.md — the embedded-website Image Studio panel this native panel replaces.
- stripe-credit-topups.md — buying the credit these generations spend.
- plan-billing.md — the Plan & Usage money screen where your credit balance lives.
Last verified 2026-10-19