Workflow Studio

Browsing & Filtering

• Switch between Thumbnail, Card, and Table view modes
• Search, category filter, favorites filter, and group filter
• Import JSON/PNG files via button or drag & drop

Groups & Badges

• Create, rename, delete groups and assign/remove workflows
• Badge management: add, rename, delete badges with custom colors shared with the Models tab (⚙ Badge button)

Side Panel & Detail Modal

• Side panel: below the workflow name, the format badge (UI / API / App) and the GenerateUI Check result badges (checked automatically on selection, results only — hover for the reasons); tabs for thumbnail, JSON viewer (format badge: UI/API/App), clipboard copy, group management
• Detail modal: rename, favorite, thumbnail change, badge assignment, tags, memo, AI summary, send to canvas, load in GenerateUI, set as default, delete
• GenerateUI Check: in the detail modal, the row below the title shows the format badge (UI / API / App) at the left, then the GenerateUI Check button and two result badges; the side panel shows the same format and result badges automatically. Nothing is saved (results stay in memory until the page is reloaded); the check takes about 20 ms (the first one after opening the page waits for ComfyUI's node list, about 10 s). Hover a ✅ / ⚠ / ❌ badge for the reasons. Conversion: converts the workflow with the same logic as GenerateUI; ❌ for unsupported formats, conversion errors or node types not installed in this ComfyUI, ⚠ for values not available here (models, LoRAs, images…) — UI-format workflows have them silently replaced with the first choice, while API-format workflows are sent as-is and rejected by ComfyUI ("Value not in list") unless you pick another value in GenerateUI (a checkpoint is replaced if "Force default checkpoint on workflow load" is on). Operability: how much of the workflow GenerateUI's fields alone can operate — the share of nodes with settings that GenerateUI shows (✅ 80%+, ⚠ 50%+, ❌ below); the tip lists the prompt/sampler fields found and the nodes whose settings must be changed in the node graph

Connecting & Loading Workflows

• Connect/disconnect ComfyUI and check connection status
• Load workflows from Workflow tab (subgraph-containing workflows are supported, e.g. Flux.2 / Qwen-Image / Z-Image / Mage-Flow templates; only ComfyUI's simplified App format [.app.json / Linear Mode] is not); Reset Workflow button re-reads the current workflow file from disk and reloads the editor; Save button (right end of the tab bar) saves the current workflow — including any edits made in the editor — as a new .json file to the Workflow tab; a filename dialog appears with the current workflow name as the default; Style checkbox and dropdown (next to Reset Workflow): enable to apply a Fooocus-style JSON style to the positive and negative prompts at generation time — style files are loaded from user/default/Workflow-Studio/style/*.json; the style's {prompt} placeholder is replaced with the original prompt, or the style text is appended if no placeholder exists
• Create Catalog button (next to the Style dropdown): generates one preview image per Style selected in the Batch tab's Style sub-tab (using the currently loaded workflow, typically T2I), then saves each result into a chosen ws_style_catalog subfolder with the Style's own name as the filename (existing files with the same name are overwritten); a modal lets you create a new destination folder or pick an existing one — separate folders are useful for grouping catalogs by checkpoint or by purpose; requires at least one Style checked in Batch tab → Style sub-tab first. Catalog button (right next to it): jumps straight to the Gallery tab's Style_Catalog sub-tab to browse the results
• Create Catalog modal — "Don't keep a copy in the Output folder" checkbox: each generation still writes a normal file to ComfyUI's Output folder first (that's simply how the workflow's own Save Image node works), but once its copy has been saved into the catalog folder, checking this deletes that Output-folder original right away — useful for large catalog runs (e.g. all 200+ styles) so the Output folder isn't flooded with near-duplicate files; if a particular style's catalog copy fails to save, its Output file is left alone rather than being deleted
• Input tab → Image sub-panel — each LoadImage card now has three buttons: Apply (unchanged), Clear (resets that card's pending selection/preview back to empty; doesn't touch the workflow node itself, since LoadImage always needs some valid filename), and Placeholder. A Placeholder Image section — collapsed by default since it's a low-frequency feature, click to expand — sits at the top of the panel with a shared default: Color mode (set Width/Height/Color; generates a solid-color PNG on the fly) or Image mode (drop one default image, reused as-is). Clicking a card's own Placeholder button immediately replaces just that card's image with the configured default — no separate Apply click needed, and with several LoadImage cards each can be replaced individually. The Placeholder config (mode, size, color, default image) is remembered across sessions

Tab Layout

• 5-tab layout — Input (Prompt + Image), Model, Settings, Feeder, Batch — Input/Model/Settings each include a Raw JSON column for instant preview and direct editing
• Input tab: Prompt (left) and Image (right, about 3:2) are shown side by side on one screen (drag-and-drop upload); when the Prompt/Image area gets narrow (about 720px or less) Image wraps under Prompt, and the Raw JSON column can be collapsed to a slim strip at the right edge with its » button (Input tab only; remembered); the Prompt area has Positive Prompt, Negative Prompt, and an Embeddings selector at the bottom — select a model, set Weight (default 1.0), then click Paste to insert (embedding:Name:weight) at the cursor position of the last focused textarea (defaults to Positive if neither is focused); a ↺ button next to each Apply button reverts the textarea to the node's currently applied value; select text (or just place the cursor on a word/parenthesis block) and press Ctrl+↑/↓ to adjust its emphasis weight in (text:weight) syntax by ±0.05 — the parentheses are removed automatically when the weight returns to 1.0
• Model tab: Checkpoint, VAE, Diffusion Model (UNETLoader / UnetLoaderGGUF / LoaderGGUF), Text Encoder (CLIPLoader / DualCLIPLoader / ClipLoaderGGUF / DualClipLoaderGGUF — type and device selectors; DualCLIP shows two clip selectors) are always shown; ControlNet and Hypernetwork (with Strength field) are collapsed by default since they're used less often — click their header to expand; LoRA (Single/Stack tabs) has its own column to the right; all selectors have a filter; LoRA Stack — Apply writes all active LoRAs to the target node and simultaneously inserts LoRA syntax and CivitAI trigger words into the Positive prompt; re-applying updates the prompt by removing inactive LoRAs and re-adding active ones
• Model tab — Highlight color: the label of each model type (Checkpoint, VAE, Diffusion Model, Text Encoder, ControlNet, Hypernetwork) and the LoRA column header turn a distinct color (default bright green) when the loaded workflow actually contains that type of node; this stays visible even while ControlNet/Hypernetwork are collapsed, so you can tell at a glance whether they're in use without expanding them; the color is customizable in the Settings tab
• Settings tab: KSampler and Latent Image side by side, each at 50% width
• LTX-2.5 and Wan2.2 video workflows also work when loaded as regular workflows in this tab (not just the dedicated Video tab): Positive/Negative Prompt detection follows LTX-2.5's LTXVDualCFGGuider / LTXVConditioning nodes to find the actual prompt text, and the Settings tab's Latent Image section recognizes Wan2.2's EmptyHunyuanLatentVideo and LTX-2.5's EmptyLTXVLatentVideo nodes (with an added Length (frames) field) instead of showing "No EmptyLatentImage node found"; generating from these workflows also gets the same extended timeout as MiniMax H3 video generations
• Raw JSON always visible in the right column of each tab — edit directly and Apply to reload the workflow; if the loaded workflow has Bypass or Mute nodes, a note listing them appears above the search bar (Bypass nodes are excluded with their wires reconnected around them; Mute nodes are excluded with no reconnection, matching ComfyUI itself); the search bar highlights matches and scrolls to them without moving the cursor into the editor, so typing right after a search can't accidentally overwrite the JSON — click into the editor first to actually edit
• The Save button (right end of the subtab bar) is hidden while the Batch or Lab subtab is active, since those work on workflow copies / their own Plan files rather than the currently loaded workflow; it reappears on Input/Model/Settings/Feeder
• Partner API nodes (Nano Banana / Gemini image nodes, etc.): GenerateUI can run workflows that contain ComfyUI's partner API nodes. These nodes need Comfy credentials in the /prompt request — ComfyUI's own screen adds them automatically, but a separate page cannot — so add COMFY_API_KEY=... (a Comfy API key issued at platform.comfy.org) to the plugin's .env file and restart ComfyUI. With the key set, GenerateUI sends the request through the plugin server, which adds the key only when the workflow contains a partner API node (the key never reaches the browser); usage is billed as Comfy credits. A Gemini image node's prompt appears in the Prompt tab, and its reference images go through LoadImage nodes in the Image tab. Sample: ws_nano_banana_2_1_t2i

Seed & Generation

• Seed control: random, fixed, increment, decrement, workflow (uses the workflow's own seed) — seed input and mode selector stacked vertically for readability
• Generate, progress display, stop, and view results
• Eagle integration: auto-save generated images to Eagle (SVG output supported too — both the standard SaveSVGNode and comfyui-tosvg's Save SVG String node)
• Alt+Click any Apply button (Positive Prompt / Checkpoint / KSampler) to Apply & Generate in one step — applies the parameter to the workflow then immediately queues a generation; only fires when the target node exists in the loaded workflow

Batch Tab — Setup

• Batch tab — enable one batch type at a time by checking the checkbox in the Batch Queue column header; Generate then runs through all queued items sequentially with Pause/Resume and Stop controls
• Batch tab — Left pane has 4 tabs: Checkpoints (folder tree with Filter/All/None; (root) header checkbox selects all), Sampler (KSampler sampler_name list with (root) checkbox), Scheduler (KSampler scheduler list with (root) checkbox), Style (flat list of all styles loaded from Workflow-Studio/style/ with All/None buttons); All/None toolbar buttons available for each tab
• Batch tab — Center pane: group-based selection with inner tabs (Checkpoint | Lora | Prompt | Workflow); Checkpoint tab shows groups defined in the Models tab — check a group header to select all its members, or expand ▶ to check individual models; group membership always reflects the current Models tab state
• Batch tab — Right pane (Batch Queue): 7 columns — Checkpoint, Lora, Prompt, Workflow, Sampler, Scheduler, Style; each column has an enable checkbox; only one type active at a time; count shown per column

Batch Tab — Batch Types

• Sampler/Scheduler batch: select one or more samplers or schedulers from the left pane, enable the column in Batch Queue, then Generate to run each value through the KSampler node sequentially; sampler/scheduler lists are fetched from ComfyUI (requires connection)
• Style batch: select styles in the left pane Style tab, enable the Style column in Batch Queue, then Generate — each selected style is applied in sequence to the positive and negative prompts; styles are applied to workflow copies so the loaded workflow is not modified; style files are re-read each time the page loads from user/default/Workflow-Studio/style/*.json
• Lora batch: for each LoRA, its syntax (<lora:name:strength_model:strength_clip>) and CivitAI trained words are automatically appended to the Positive prompt — rebuilt from the original prompt each time, not accumulated; the prompt is automatically restored to its pre-batch state when the batch completes or is stopped; if a selected LoRA is not yet recognized by ComfyUI's model list, a warning toast is shown (Refresh or restart ComfyUI)
• SPA-side wildcard expansion (A1111-style): when prompt text in non-ImpactWildcard nodes (e.g. CLIPTextEncode) contains __name__ syntax, the SPA expands it at generation time by randomly picking a line from the matching file in the WFS wildcard folder; nested wildcards are re-expanded up to 5 passes; unresolved wildcards are passed through unchanged; ImpactWildcardEncode/Processor nodes are skipped (handled server-side by Impact Pack); works in both single and batch generation

Model Tab — LoRA Details

• Three ways LoRAs are attached: a chain of standard LoraLoader nodes (one LoRA per node — add more by chaining additional nodes), a single Lora Loader (LoraManager) node (from the ComfyUI-Lora-Manager custom node pack) that holds a list of LoRAs internally, each with its own active/model-strength/clip-strength, or ComfyUI's native Load LoRA (Model) + Load LoRA (Text Encoder) node pair (v0.40+; each holds up to 20 rows of LoRA / strength / enabled — the Model node takes Str M, the Text Encoder node takes Str C, and Apply writes both nodes together; API-format workflows only for now, because ComfyUI frontend 1.55.17 cannot add rows to these nodes in its own graph editor); the Single/Stack tabs below adapt automatically depending on which type the target node is
• Single tab: pick one LoRA + Str M/Str C, then Apply — for a Lora Manager node this replaces its entire internal LoRA list with just this one entry, discarding any others it had; the native Load LoRA nodes likewise have all their rows replaced by this single row
• Stack tab — Use Stack Group checkbox (shown only when a Lora Manager node exists in the workflow): OFF (the default whenever a workflow is loaded) shows and edits the LoRAs actually configured in the workflow's Lora Manager node itself; ON shows and edits the "Stack" group registered in the Models tab instead; switching either direction clears the node's LoRA list first, then loads it from the newly selected source; switching back to OFF restores exactly the LoRA list that was present when the workflow was loaded (captured as a snapshot at load time)
• Stack tab controls: each row has an active checkbox and Str M / Str C fields; the header "Stack" checkbox toggles all rows at once; the +/- step buttons adjust the strength of all currently active rows together; a "Showing: LoRAs currently in workflow" / "Showing: registered Stack group" label indicates which source is currently displayed; Apply writes the full list back to the target node and also appends LoRA syntax + CivitAI trigger words to the Positive prompt
• Caution for CLIP Text Encode edit+ (CLIPTextEncodeEditPlus) nodes: when a Lora Manager node's trigger_words output feeds this node's text1 input (RAW/EDIT/front/back modes combine text1 with the editable text_edit field), trigger words are already included automatically at generation time; clicking a LoRA Apply button or turning on Use Stack Group additionally writes LoRA syntax/trigger words into text_edit, duplicating them — leave Use Stack Group off and avoid the LoRA Apply buttons if you want the workflow's original prompt and LoRA composition to stay unmodified
• Bypass button (⛔, in the LoRA column header, next to Refresh Stack group): forces the target LoRA node's strength to 0 — strength_model/strength_clip for a standard LoraLoader, every entry's strength/clipStrength for a Lora Manager node (its LoRA list is kept intact, not replaced), or every row's strength on both native Load LoRA nodes (Model and Text Encoder; rows kept) — without touching the actual ComfyUI node's mode; click again to restore the exact values that were there before toggling; targets whichever node Single/Stack Apply default to (the workflow's Lora Manager node if it has one, else the first LoRA node); clicking a Single or Stack Apply button clears the bypass state so it can't silently reassert itself on a later toggle

Image Loop mode

Requires the comfyui-image-feeder custom node. Controls ImageFeeder nodes and runs continuous generation loops over an image library stored in user/default/image-loop-data/.

• Left pane — Node settings: select the target ImageFeeder node from the dropdown; edit all node parameters (Directory, Sort Mode, Index, Start/End Index, Batch Size, Seed, Use Selection); click Apply to write changes to the loaded workflow
• Left pane — Presets: save the current directory + selection as a named preset; load or delete saved presets
• Left pane — Run: After gen mode determines index behavior after each generation — Loop (wrap back to 0 and continue indefinitely), Increment (advance index and stop when all images are exhausted), Fixed (always use the same index); click Run to start the loop, Stop to interrupt
• Center pane — Folder tree: browse subfolders inside image-loop-data; (root) is selected automatically on load; click a folder to load its images; click ↺ to reload the tree
• Center pane — Image grid: displays thumbnails of all images in the selected folder; check individual images to add them to the selection; All / None buttons select or clear the entire folder; click an image to open the preview panel
• Right pane — Preview: fixed at the far right of the layout; shows the clicked image at larger size with filename, resolution, and file size; during a RUN the preview updates automatically to show the current processing image
• Status bar: shows the current folder path and how many images are selected out of the total in the folder
• Seed during Run: uses the right-pane seed setting (Random / Fixed / Increment / Decrement) — the ImageFeeder's own Seed field controls random sort order only
• Index sync: after each generation the node returns the next index via WebSocket; the Index field updates automatically so the display stays in sync

Gallery mode

Uses the built-in WFS_GalleryFeeder node (no external plugin required). Feeds images from a Gallery group into a continuous generation loop.

• Left pane — Node: select a WFS_GalleryFeeder node from the dropdown and click Apply to link it to the workflow; select the source group (defaults to __Feeder__), Sort Mode, Index (current image position), and Seed
• Left pane — Run controls: After gen — Loop (wrap to start and repeat), Increment (advance and stop at last image), Fixed (always use the same index); click Run to start the loop, Stop to interrupt after the current generation
• Center pane — Group image grid: shows all images in the selected group; click a thumbnail to select it and jump to that index; the selected image is highlighted
• Right pane — Preview: displays the currently selected input image; updates when a thumbnail is clicked
• __Feeder__ group: reserved group pre-created automatically; cannot be renamed or deleted; add images to it from the Gallery tab using the F overlay button on each thumbnail
• WFS_GalleryFeeder canvas controls: the node also has Run / Stop / After Gen widgets added directly on the ComfyUI canvas — these work the same as the WFM UI controls and allow running the gallery feeder loop without opening WFM

Setting subtab — Image & Columns

• Left pane — Image: drop or click to select an I2I source image; it is uploaded to ComfyUI's input folder and used for every iteration unless "Use generated image for next" is checked
• Left pane — Use generated image for next: from iteration 2 onward, feeds the previous iteration's first output image back in as the I2I source instead of the original dropped image (iteration 1 always uses the original)
• Center pane — 4 independent columns: Checkpoint, VAE, Prompt, KSampler; each column keeps its own list of keyframes rather than sharing a row grid
• + / − per column: + appends a new keyframe at the next free iteration number (up to the Batch count) and opens its edit modal immediately; − removes the last keyframe (iteration #1 can never be removed); any keyframe other than #1 can also be deleted individually from inside its own edit modal via its Delete button, not just the last one
• Click a cell to edit it: iteration #1 sets the baseline value (leave it blank to keep the loaded workflow's own setting); iteration #2+ also lets you choose which iteration it starts applying from, plus a "revert to #1's setting" checkbox
• Effective value at iteration N: the latest keyframe with iteration ≤ N is used and carries forward until the next keyframe changes it; "revert to #1" reuses iteration #1's value (or the workflow default if #1 is blank) instead of specifying a new one; lowering the Batch count (by hand, or by loading/applying a plan) below an existing keyframe's iteration number doesn't delete or renumber that keyframe — a warning toast appears, and the keyframe simply stays dormant (never reached by the run loop) until Batch count is raised again. This whole-row resolution applies as-is to Prompt and KSampler; the Model column instead resolves its three fields (Checkpoint/LoRA/VAE) independently — see below
• Lab never edits the workflow shown in Input/Model/Settings — every iteration runs on a fresh clone of the loaded workflow, so keyframes here never affect the other subtabs
• Prompt cell editor extras: Get from GenerateUI fills Positive/Negative from the workflow currently loaded in GenerateUI; Get from Image extracts a prompt from the image currently loaded in Lab's own Image drop zone (same detection as the Metadata tab; no separate file picker); Style row — the Apply button appends whichever style is currently selected in the Style dropdown at the top of the GenerateUI toolbar to the Positive/Negative text below, comma-separated after any existing text (never clears it), then checks the Style checkbox and shows the applied style's name next to it (not on the button) — the style NAME always comes from that top dropdown (Lab has no picker of its own), and clicking Apply works regardless of the top toolbar's own Style enable checkbox; unchecking the Style checkbox only clears that name label — it does not remove the already-appended text from Positive/Negative, which stays there for you to edit or delete by hand
• Left pane — T2I workflow (no source image): check this when the loaded workflow is text-to-image (no LoadImage node). It skips the "drop a source image first" requirement, ignores any dropped image and the Model/Prompt/KSampler keyframes still apply normally; the Image drop zone and "Use generated image for next" are greyed out while it's on (any previously dropped image is kept, not deleted, in case you switch back to I2I); the setting is saved with the plan as t2i_mode
• Wildcards: Positive/Negative prompt text in Prompt column keyframes supports the same A1111-style __name__ syntax as the main GenerateUI (see Prompt tab's Wildcards help above) — each keyframe's text is expanded fresh right before that iteration runs, so every iteration can draw a different random line even when reusing the same keyframe
• Prompt cell editor also has Clear (empties both Positive and Negative) and Get from Previous (copies both Positive and Negative from the keyframe immediately before this one in the same column — e.g. editing #3 copies #2's prompt wholesale; not shown on keyframe #1, which has no earlier row to copy from)
• Keyframe #1 in every column shows the currently loaded workflow's own live setting instead of a blank placeholder — for the Model column this covers Checkpoint and VAE only (LoRA is never live-reflected, since there's no reliable way to infer "the" active LoRA back out of a workflow node) — both in its grid cell (dashed border) and pre-filled into its edit modal, for as long as it hasn't been explicitly saved with an override; saving it (even without changing anything) locks that value in as a real override and the dashed/live styling goes away; switching to the Lab subtab always refreshes this against whatever is currently loaded in GenerateUI
• Bypass checkbox (every keyframe, including #1): skips that row entirely when picking which setting applies at a given iteration — as if the row didn't exist — so whatever was active before it (an earlier keyframe, or ultimately nothing) just keeps running; Lab-internal only, it never touches the actual ComfyUI node's mode; disables that row's value fields and its Revert checkbox while checked (the two are mutually exclusive); the cell shows an amber "⏭ Bypassed" label, which takes priority over both the Revert and live-value display
• Model column header's C / L / V buttons pick which independent keyframe list — Checkpoint, LoRA (Single-only, no Stack support here), or VAE — the shared cell list, its +/-, and its edit modal all currently operate on. Each of the three is its own timeline with its own keyframes, exactly like Prompt/KSampler; they only ever look merged because they share one column's worth of screen space. Adding, removing, or editing a keyframe while viewing one never touches the other two. Each button turns the same highlight color as GenerateUI's Model tab (configurable in Settings) when the loaded workflow actually contains that node type. If a LoRA is set but the workflow has no LoRA node at all, Lab warns once per Run and skips applying it — unlike VAE, it never auto-inserts a LoRA node, since that would require rewiring the Checkpoint's model/clip outputs through it
• Checkpoint / LoRA / VAE each carry forward independently, the same effective-value rule as every other column (see above): a keyframe in one never resets the other two to the workflow default. A field left blank in the edit modal shows "(inherits: ...)" as its placeholder instead of "(workflow default)" when an earlier keyframe in that same list already set something, so it's clear what actually applies. "Revert to #1's setting" and Bypass — like +/- — only ever affect whichever ONE of the three is currently selected by the C/L/V toggle, never the other two
• Bypass LoRA node checkbox (LoRA keyframe's own edit modal only): forces that keyframe's strength_model/strength_clip to 0 at apply-time, standing in for ComfyUI's own node Bypass (mode:4) — the workflow used here is already converted to API format, which has no mode concept, so zeroing strength is the behavioral equivalent. Disables the strength fields while checked; independent of the row-level Bypass checkbox above, which skips the whole row instead of touching the node
• Apply LoRA syntax + trigger words to Positive prompt checkbox (LoRA column only): when checked, appends <lora:name:strengthModel:strengthClip> plus that LoRA's cached CivitAI trigger words to the Positive prompt, comma-separated, at apply-time — the same format GenerateUI's own Model tab Apply button writes. Switching keyframes (a different LoRA, this checkbox turned off, or the row Bypassed) always strips exactly what the previous iteration injected before adding anything new, so a batch never accumulates every LoRA it has used. Disabled automatically while Bypass LoRA node is checked
• A single click on a keyframe cell selects it (blue outline) instead of opening it — double-click to open the edit modal as before. Each column's header (Model / Prompt / Ksampler) also has ▲ / ▼ buttons that swap the selected keyframe with its immediate neighbor to reorder them without retyping anything; keyframe #1 (the baseline) can never move, and nothing can be swapped into its slot
• Prompt column header's PG button: pick one of the Prompt tab's preset groups (Table view's Presets Group, the same groups used by the Batch tab's checklist) and replace the entire Prompt column with one keyframe per preset in that group's order, starting at #1 (#1 is overwritten, not appended after). If the group has more presets than the current Batch count, Batch count is raised automatically to fit (capped at 50, the Batch input's own limit); anything still beyond that shows the usual "keyframes beyond Batch count" warning instead of being silently dropped

Setting subtab — Run & Plan files

• Right pane — Batch: number of iterations to run; Note: free-text memo saved together with the plan
• Run / Pause / Cancel: Run starts the batch loop; Pause/Resume freezes it between iterations; Cancel interrupts the current generation and stops the loop
• Plan Save vs Save As: Plan Save silently overwrites the currently loaded plan (or asks for a name the first time); Save As always asks for a new name, even while a plan is already loaded
• Plan Load: drop a plan's .json file, or any of its index-image PNGs, onto the PLAN box (or click it to browse) — a dropped .json is read directly; a dropped .png is read directly too if it carries embedded plan data (every index image since v0.3.90 does, in a wfm_lab_plan chunk — see below), falling back to fetching a same-named .json from the server for older index images that predate this
• Plan Clear resets the Setting tab to an empty plan (asks for confirmation first)
• Plan files are stored in user/default/Workflow-Studio/lab_plan/ as ws_labplan_<name>.json plus a ws_labplan_<name>.png index image — a contact sheet of up to 9 result thumbnails (3 per row) generated automatically whenever a plan with results is saved. The ws_labplan_ prefix is added automatically by Plan Save/Save As (type just the plain name when prompted) so plan files are easy to pick out among other files in that folder
• Eagle auto-save (configured in the Settings tab) applies to every image Lab generates, the same as GenerateUI's own Generate button
• Plan JSON subtab: shows the current Setting tab's plan as raw JSON; Refresh re-reads it from the Setting tab (discarding any unapplied text edits), Apply to Setting parses your edits and writes them back into the Setting tab (columns, note, batch count, chain-image, source image, results) — the same effect as loading that JSON as a plan file, without needing to save it first
• Each saved plan records the filename of the workflow that was loaded in GenerateUI at save time (workflow_filename in the Plan JSON). After loading a plan, an Open Workflow button appears in the PLAN box — click it to load that exact workflow file back into GenerateUI (asks for confirmation, since it replaces whatever is currently loaded)
• Right pane — Save index image to Output on Run: when checked, every time Run finishes it builds the same contact-sheet index image used for Plan files and saves it directly into ComfyUI's own Output folder as Lab_index_<counter>_.png (auto-numbered like a normal generated image, never overwriting a previous run's). Once saved, it also goes through Eagle auto-save (if enabled in the Settings tab) just like every other Lab-generated image — no separate checkbox for that, it follows the same global toggle. This is independent of Plan Save, which still always writes its own index image next to the plan file in lab_plan/ regardless of this checkbox; this setting is saved with the plan as save_index_on_run
• Every index image PNG — whether from Plan Save/Save As or from Save index image to Output on Run — carries the entire plan (columns, note, batch count, chain-image/T2I settings, workflow filename, results) embedded in it directly as a PNG wfm_lab_plan chunk, so the Output-folder copy is self-contained and works as a Plan Load source too even though it has no matching .json next to it anywhere

Results subtab

• Left pane shows the source image used for the run
• Center pane shows up to 9 generated images in generation order; click a thumbnail to view it enlarged
• Loading a saved plan restores its Results grid from the image list recorded in the plan file

Form / Table

• Two top-level tabs: Form is the original one-item-at-a-time editor described below (AI Assistant / Presets / Wildcard / Style panes); Table shows the same underlying data all at once as editable spreadsheets — useful once there are more than a handful of presets, wildcard files, or styles to manage

AI Assistant & Translation

• AI assistant (Ollama / LM Studio / Lemonade / Unsloth): chat for prompt consultation, image attachment (vision models); click the ⚙ Settings button to choose backend, connection URL, model, Thinking mode, Max tokens, and unload the loaded model (with Ollama, every model loaded in Ollama on localhost is unloaded, decision models included — the same as Settings → VRAM Management) — settings are independent from the AI TOOL and Tagger tabs
• Apply AI responses to GenerateUI prompts
• Translation: JA↔EN, ZH↔EN

Presets

• Preset management: create, edit, positive/negative prompt clipboard copy (PP/NP)
• Preset Manager: browse all presets, favorites, and group-based filtering
• Group management: create groups, assign/remove presets, delete groups
• GenUI Set: apply preset prompts directly to GenerateUI

Wildcards

• Wildcard toolbar: one-click buttons to insert wildcard syntax ({|}, {n$|}, __|__, <lora:>, etc.); wraps selected text
• Wildcard file manager: create/edit/delete .txt/.yaml wildcard files; click filename to insert __filename__ at cursor

Style

• Right pane's Wildcard/Style tab bar switches the whole panel between the wildcard tools above and this Style manager — same right pane, two modes
• Create/edit/delete registered Styles (the same ones used by GenerateUI's Style dropdown, Batch tab, and the Style Catalog): click a name in the list to edit it, or + New for a blank entry; Name, Positive prompt (supports the {prompt} placeholder — replaced with the user's own prompt, or appended after it if omitted) and Negative prompt (optional)
• Renaming a style keeps its position in whichever file it was originally defined in; new styles are saved into a dedicated custom.json inside the style folder so the bundled style packs are never modified directly; a name must be unique across all styles
• Saving, renaming, or deleting a style immediately refreshes GenerateUI's Style dropdown, the Batch tab's style checklist, and the Style Catalog's name list — no reload needed
• Each entry in the list shows its source file as a small badge next to the name (e.g. sdxl_styles_diva.json); while editing an existing style, that filename also appears above the Positive prompt field, and a + Add to this file button appears next to Save — click it to clear the form for a brand-new style that gets appended to that same file instead of the default custom.json

Table View

• The Table tab has four sub-tabs of its own: Presets, Presets Group, Wildcards, and Style — each an editable table built from the exact same data as the Form tab, so changes on either side stay in sync
• Every table shares a left-most auto-numbered # column: click a number to select that row (highlighted red) — multiple rows can be selected at once; the toolbar's Delete button removes every selected row in one confirm, and Deselect clears the selection. This replaced per-row delete buttons, which were too easy to misclick
• Double-click a row's number to open a larger prompt-editing modal instead of the small in-table textarea. Presets and Style show Positive/Negative toggle buttons above one shared textarea (switching preserves whatever you typed on the other side); Wildcards shows just the file's content. Save writes the change back and closes the modal; Close discards it
• The toolbar's + New ... button adds a blank row at the top with small ✓ (Add) / ✕ (Cancel) icons in place of its number; fill in the fields and click ✓ to create it, or ✕ to discard the row without saving
• Presets table — the ★ (favorite) and B (Batch group) columns work like toggle switches: click to turn them gold/yellow, click again to clear; the toolbar's BC button clears every preset out of the Batch group at once, same as the Form tab's Preset Manager
• Presets table toolbar — PP Copy / NP Copy copy the single selected row's positive/negative prompt to the clipboard; the group select + Add to Group adds every currently selected preset to the chosen group in one click. Doing the group assignment from here (search/select presets, then pick from a short group list) replaced the old per-group preset picker, which became unusable once there were many presets
• Presets Group table — create, rename, and delete groups; each group's members are shown as removable badges (✕). The reserved Batch group is not listed here — it's managed entirely through the Presets table's B column and BC button instead
• Wildcards table — same files as the Form tab's Wildcard file manager; editing the File path or the Ext dropdown renames the file (saves the content under the new name, then removes the old file)
• Style table — same styles as the Form tab's Style manager, editable inline the same way as Presets
• Presets table toolbar — the ★ and B sort buttons (next to the search box) bring favorited / batch-selected presets to the top of the list; both can be enabled together (★ takes priority, B breaks ties), and everything else keeps its original relative order
• Style table toolbar — select exactly one row whose File badge isn't custom.json to enable + Add to this file: it adds a blank row targeting that same file (shown as a badge in the File column even before saving) — the same capability as the Form tab's Style manager (see above); custom.json entries and multi-row selections leave the button disabled, use the regular + New Style button for those instead

Overview

Drop a ComfyUI-generated PNG/WebP or workflow JSON to instantly extract and view the embedded model and prompt information.

• Left column: drop zone (image preview for PNG/WebP) and file info; click or drop to load
• This is now a sub-tab inside the Gallery tab (to the right of Style_Catalog), rather than its own top-level tab — everything else about it works exactly the same

Extracted Information

• Center column: Checkpoint, VAE, Diffusion Model, and Text Encoder lists extracted from the workflow, plus (since v0.7.14) the LoRA list and Prompt list that used to be in the right column
• Right column (v0.7.14): Settings — image size (width×height) and, when the workflow has a KSampler-type node, its Seed / Steps / CFG / Sampler / Scheduler / Denoise values
• Right column, Nanobanana section (v0.7.14): shown only for images from ComfyUI Comic Creator's Nanobanana tab opened via the Gallery tab's Metadata button (needs a matching entry in that folder's history.jsonl log) — engine, model, image size, seed, timestamp, and the prompt/negative prompt actually used; replaces what would otherwise be a "no metadata found" error, since these images have no embedded ComfyUI workflow
• Prompt actions — Copy: copy to clipboard; GenUI:P/N: set GenerateUI positive/negative prompt; Prompt:P/N: set Prompt tab preset positive/negative

Supported Formats

• Supported: ComfyUI PNG/WebP/MP4/JSON (standard + Flux.2 / Qwen-Image / Z-Image / Mage-Flow subgraph workflows; MP4 reads the workflow/prompt container tags written by SaveVideo, including all-in-one video nodes like MiniMax H3 ImageToVideo), SD WebUI, SD Forge, Fooocus. Model extraction covers UNETLoader, UnetLoaderGGUF, UNETLoaderGGUF (e.g. HiDream GGUF), CLIPLoader, DualCLIPLoader, TripleCLIPLoader, and QuadrupleCLIPLoader (e.g. HiDream 4-CLIP).

General

• UI language and summary language
• Theme selection (13 presets) with customization: color overrides, background patterns (stripes, polka dot, checkerboard, SVG tiling), and font selection (15 Google Fonts including Japanese display fonts, plus the system default)
• All sections are collapsible accordion panels

Connections

• ComfyUI connection URL and test
• AI Assistant settings have moved out of this tab — the Prompt tab, Tagger tab, and AI TOOL tab each have their own ⚙ Settings button (backend, URL, model, Thinking mode, Max tokens, unload model), saved independently
• Eagle integration URL and auto-save toggle
• G'MIC-Qt Integration: path to the G'MIC-Qt executable (gmic_qt.exe) used by the Image Edit tab's G'MIC filter (Edit with G'MIC); Save stores it — see the Image Edit help for installing G'MIC-Qt
• Decision Model: its own section, independent of the AI TOOL / Tagger LLM/VLM backends so it can be used alongside them — backend, URL, model and a default probability threshold (answers below it are treated as suggestions to confirm). Unsloth: Laya models (laya / laya-multilingual / laya-english / laya-typed-decisions); requires Settings → API → Decision API → Serve requests in Unsloth Desktop (otherwise HTTP 404 "The Decision API is off") and either UNSLOTH_API_KEY in .env or Keyless API access → "Chat and inference". Ollama (0.35+): lists installed models whose capabilities include "decision" (tev1, tev1:0.8b, nimble — ollama pull first; ↻ refreshes the list); no key needed. Test sends one yes/no question with the unsaved form values; the first request loads the model.
• VRAM Management (Ollama): right before every image generation from Workflow Studio, unload the models Ollama has loaded to free VRAM (off / only as much as needed to reach a target free VRAM / everything every time); free VRAM is measured with nvidia-smi; "Unload all now" unloads them immediately; the same "Unload all now" is also in the sidepanel A tab → Settings → VRAM (Ollama). Running a workflow from the ComfyUI canvas itself is not covered

Workflow Defaults

• Workflow data folder path
• Models Folder: add extra model root folders (e.g. Stability Matrix's Models) — their subfolders (StableDiffusion / Lora / VAE / ControlNet / TextEncoders / DiffusionModels / Embeddings / HyperNetworks, or ComfyUI names like checkpoints / loras) are listed in the Models tab in addition to ComfyUI's own folders; separate several roots with ; — Apply saves, Default clears
• Gallery Output Folder: the ComfyUI output folder the Gallery tab browses — leave blank to use ComfyUI's default output directory; Apply takes effect immediately, Default resets it, and the folder currently in use is shown below the field
• Default workflow setting
• Default Checkpoint: when "Force default checkpoint on workflow load" is on, every checkpoint loader node's model is replaced with the chosen checkpoint whenever a workflow is loaded into GenerateUI (a toast shows when it's applied) — avoids errors or garbled images caused by a model name saved in the workflow that you don't have; Refresh reloads the checkpoint list, Save stores the setting
• Wildcard Integration: link WFS wildcard dir to ComfyUI-Impact-Pack wildcards (directory junction on Windows / symlink on other OS); existing files migrated automatically

Editor Customization

• Text Size: one slider (10–28 px) adjusts font size for all prompt and chat textareas at once — Generate UI positive/negative prompts, AI Assistant chat input, Preset positive/negative, Wildcard prompt and file editor, and Metadata prompt full preview; takes effect immediately and saved with Save Settings
• Video Volume: one slider (0–100%) sets the playback volume of the Video tab preview and the Gallery detail / lightbox / compare video players; the level set here (or changed with any video's own controls) carries over to the next video opened anywhere in the app
• RAW JSON Colors: customize the 6 syntax highlight colors for the Raw JSON editor in Generate UI — Default Text, Name/Scheduler, Title, Width/Height, Prompt/Text, Image/File; changes apply immediately on color pick; Reset Defaults restores the original color scheme
• GenerateUI Model Tab Highlight: pick the color used to mark Checkpoint/VAE/Diffusion Model/Text Encoder/ControlNet/Hypernetwork labels and the LoRA column header in GenerateUI's Model tab when the loaded workflow actually contains that type of node; default bright green; changes apply immediately, Reset Defaults restores it

Data & Misc

• Data Management: export core settings, metadata, and prompts to a JSON file, or import to restore. After importing, restart ComfyUI.
• Full Backup (ZIP): unlike the JSON export above, also includes folder-based data (AI Skills, Lab Plans, Video Plans, Video Edit projects, Style presets) and the Tagger database — everything the JSON export can't represent. Restoring overwrites existing files; restart ComfyUI afterward.
• Two opt-in checkboxes above the Full Backup buttons additionally include ComfyUI's default workflows folder and the Impact Pack's wildcard folder in the export — both export-only, never restored automatically; copy the ZIP's _external/ folder back by hand if you want them. A third checkbox includes the clips, BGM, sounds and overlay clips referenced by saved Video Edit projects (projects only store references to files in ComfyUI's input folder) — unlike the other two, these are restored into the input folder, skipping any file that already exists there.
• CivitAI Host: choose between civitai.com (SFW only) and civitai.red (unrestricted) — determines which site opens when clicking a model link in the Models tab CivitAI panel
• CivitAI API Key: optional key for authenticated CivitAI access from the Models tab (get it at civitai.com → Account Settings → API Keys); stored in settings.json but left out of the JSON export and Full Backup, and the CIVITAI_API_KEY environment variable takes priority when set
• Windows Stability: "Use the Selector event loop on Windows" switches ComfyUI's asyncio loop from Proactor to Selector (applied at the next ComfyUI start). Turn it on if ComfyUI freezes entirely after switching Models lists that load many preview images; the trade-offs are no asyncio subprocess support and a connection limit of about 512. The same switch is available through the WFS_SELECTOR_LOOP=1 environment variable

Browse & Organize

• Node Browser: search by name/description/alias/tag, filter by category, package, tag, group, favorites
• Card and Table view modes with pagination
• Favorite nodes and add custom tags for organization

Groups & Sets

• Create, rename, delete node groups and assign/remove nodes
• Node Sets: create reusable node collections with descriptions, tags, and link definitions between nodes

Side Panel & Multi-select

• Side panel: Details (class name, package, category, description, flags), I/O Spec (inputs/outputs with types and defaults), Groups management
• Multi-select: Ctrl+click to toggle individual nodes, Shift+click for range selection; bulk action bar appears with add to group / remove from group / create & add group / bulk favorite / unfavorite

Browsing

• Browse images in the ComfyUI output folder — set the folder path in Settings > Gallery Output Folder
• 3-column layout: folder tree (left) | image grid (center) | detail panel (right)
• Thumbnail and Table view modes; double-click any image to open fullscreen lightbox
• Toolbar filters: favorites (★), text search (filename / tag / prompt), tag filter, group filter, sort by date/name
• Four sub-tabs at the top of the Gallery tab: Output (this browser), ImagePrompt, Style_Catalog, and Metadata — the last one embeds the full Metadata Tab (see its own help page) so you can drop an image there to inspect its embedded model/prompt data without leaving Gallery

ImagePrompt Gallery

• Second sub-tab next to Output (top of the Gallery tab) for browsing a visual prompt library — manages the ws_image_prompt folder inside the ComfyUI output directory (created automatically)
• Same 3-column layout: folder tree (left) | thumbnails (center) | prompt builder (right). Click a thumbnail to preview it and its prompt text — this does not add it to the prompt yet
• "+ Add" appends the previewed image's prompt as a chip under "Selected Prompts"; chips can be removed individually (×) or all at once ("Clear All"); "Save" edits and persists the prompt text for that image
• "Final Prompt" combines all chips into one comma-separated text (also freely editable); "Copy" copies it to the clipboard. Prompt text is stored as a plain .txt file next to each image, so anyone can add their own entries by dropping an image + matching .txt file into a subfolder

Style_Catalog Gallery

• Third sub-tab (top of the Gallery tab) for visually picking a registered Style by its preview image — manages the ws_style_catalog folder inside the ComfyUI output directory (created automatically); populated by the GenerateUI tab's Create Catalog button (see GenerateUI Tab help)
• Same 3-column layout: folder tree (left) | thumbnails (center) | Positive/Negative prompt panel (right). Click a thumbnail to read the Positive/Negative prompt actually embedded in that generated image, each with its own Copy button
• Select as Style button: matches the selected image's filename (without extension) against a registered Style name and switches the GenerateUI tab's Style dropdown to it — a visual shortcut into the existing named-Style system, not a one-off apply of the embedded prompt (if the Style was renamed or deleted since the catalog image was created, a "no matching style" toast is shown instead)
• Load in GenerateUI / Open in Metadata Tab buttons: read the workflow embedded in the catalog image itself (the catalog copy carries the same PNG metadata as the original output image) and either load it straight into the GenerateUI editor or open the image in the Metadata tab for inspection — no need to hunt down the original file in the Output folder

Folder & Selection

• Folder tree: click to load images, expand with ▶; "+ New" creates a subfolder inside the selected folder, "Del" deletes it with all contents
• Multi-select with Ctrl+click — bulk bar: select group → 'Add to Group' / 'Remove from Group'; 'Favorite All' / 'Unfavorite All'; 'Compare' (2–4 images); 'Move To...'; 'Export' (downloads all selected images as a ZIP file); 'Create PSD' (combines the selected images into one layered PSD file); 'Edit as Layers' (opens the selected images in the Image Edit tab, each as its own layer); 'Delete File'
• F button (cyan overlay, top-left of each thumbnail): toggle the image in/out of the __Feeder__ group with a single click; active state stays visible (cyan) when the image is already in the group; use this to quickly queue images for the Feeder tab Gallery mode

Detail Panel

• Detail panel — Info tab: filename, size, dimensions (image width×height) or video duration, date, tags (add/remove), memo; download icon (on image hover) to download the single image; "Move To..." moves the image to another folder, "Delete File" removes it permanently. In the Move To dialog (also from the bulk bar), type in the filter box to narrow the folder list by name or path (space = AND); Enter moves to the first match.
• Detail panel — JSON tab: displays workflow JSON from PNG embedded data (prompt / workflow keys) or from metadata saved by the Generate UI tab; 'Copy & Send Canvas' button copies to clipboard and stores the workflow for title-drag to canvas
• Detail panel — Groups tab: create, assign, remove, rename, and delete groups per image; the __Feeder__ group is reserved (shown with 🔒) and cannot be renamed or deleted — rename and delete buttons are disabled when it is selected
• Detail panel — Prompt tab (selected by default): lists positive/negative prompts found in the embedded workflow; hidden for images in a cc_nanobanana folder, since those carry no embedded ComfyUI workflow — a Nanobanana tab (v0.7.14) appears there instead, shown only when that folder's history.jsonl generation log (written by ComfyUI Comic Creator's Nanobanana tab) has a matching entry for the selected image: engine, model, image size, seed, timestamp, and the prompt/negative prompt actually used

Actions Toolbar

• Metadata button (green, in the detail panel tab bar): opens the selected image in the Metadata tab for full embedded-data inspection; Alt+click on any image thumbnail has the same effect
• Load GenUI button (blue, in the detail panel tab bar): loads the embedded ComfyUI workflow from the selected image directly into the GenerateUI tab and switches to it; shows a warning toast if no workflow is embedded or the format is not supported
• Tagger button (purple, in the detail panel action row): opens the selected image directly in the Tagger tab's Single mode for instant tagging
• Image Edit button (toolbar, next to Refresh): sends the currently selected image to the Image Edit tab; if layers already exist the image is added as a new layer scaled to fit the canvas, otherwise it becomes Layer 1; PSD files are fully decomposed into their original layers instead of being flattened into one image
• Send GenUI Image button (toolbar, next to Image Edit): uploads the selected image to ComfyUI and sets it as the input for the first LoadImage node in the GenerateUI tab; automatically switches to GenerateUI → Input → Image; requires a workflow with at least one LoadImage node to be loaded first
• Send to LI node button (toolbar, next to Send GenUI Image): uploads the selected image and writes its filename into the image widget of the currently selected node on the ComfyUI canvas (falling back to the first LoadImage-type node found) — same destination as Image Edit tab's Send to LI node; requires Workflow Studio to have been opened from ComfyUI's top menu button
• Send to LV node button (toolbar, next to Send to LI node): the video equivalent — uploads the selected video and writes its filename into the file widget of the currently selected node, which must be ComfyUI's native Load Video node; only enabled when the selected item is a video (mp4/webm); requires Workflow Studio to have been opened from ComfyUI's top menu button
• Send CC Layout / Send CC Image buttons (toolbar, shown only when this Gallery is opened inside ComfyUI Comic Creator; v0.8.11): Send CC Layout sends the selected image to the Layout tab's selected panel / overlay (an MP4 goes to the Video tool); Send CC Image switches to Comic Creator's Image tab and loads the selected image there (as a new layer if a document is open, otherwise as a new canvas; videos are not supported)
• Create PSD bulk button: combines all selected images into a single layered PSD file and downloads it — each image becomes its own layer (named after the file), positioned top-left on a canvas sized to the largest selected image; the last selected image ends up on top Convert... bulk button (shown when audio/video files are selected): converts audio files — or extracts the audio track of videos — to FLAC / MP3 / Opus / M4A / WAV (bitrate, sample rate, channels selectable) into the same folder as new files; prompt/workflow tags are carried over for formats that can hold them (WAV cannot), favorite/tags/memo/groups can be carried over, and the originals can optionally be deleted afterwards.
• Edit as Layers bulk button: switches to the Image Edit tab and opens all selected images at once, each as an independent layer (video files in the selection are skipped); the last selected image ends up on top
• Semantic Search (v0.8.2): the S button next to the search box turns semantic search on. When ON, the search box finds images by meaning using Gemini Embedding 2 or EmbeddingGemma 2 running in Ollama (e.g. 'sunset city street') - press Enter to search; results are ordered by similarity with a score badge. When OFF it is the normal filename/tag/prompt search. Turning S on also shows a second toolbar row with Similar, the update button, the settings button and the result count. The settings button (gear) opens a window to build/update/delete the index for the selected folder (optionally with subfolders); choose the model with the radio buttons (Gemini needs GEMINI_API_KEY in the plugin's .env + a ComfyUI restart; EmbeddingGemma 2 needs Ollama running locally with the model downloaded: ollama pull embeddinggemma-2:740m or embeddinggemma-2:440m). Switching model or vector size needs 'Rebuild all'. Searches cover the selected folder tree; sort and tag/group filters do not apply to semantic results
• Similar toggle and update button (second toolbar row, shown while S is ON): Similar shows images similar to the selected one (an image not yet indexed is embedded on the fly). Selecting another image keeps the list as is; press the update button to show images similar to the newly selected one, or press Similar again to return to the normal list. Changing folder, Clear filters or turning S off also leaves similar mode
• EmbeddingGemma 2 runs in Ollama (the built-in ONNX runtime was removed, so onnxruntime-gpu is no longer needed for it). On the Model tab set the Ollama URL (default http://localhost:11434; other hosts must be listed in WFS_ALLOWED_BACKEND_HOSTS) and the model size: 740m (text + image + audio) or 440m (text + image, smaller). Both return identical vectors, so you can switch sizes without rebuilding; the ':latest' tag is the same as 740m and is used when 740m is not downloaded. 270m and 570m cannot embed images and are not offered. Indexes made with the earlier ONNX version keep working (the vectors match closely; use 'Rebuild all' to regenerate them exactly). Images are sent 4 at a time (about 0.1-0.2 s per image with an NVIDIA GPU). The model is unloaded from VRAM when indexing finishes and Ollama reloads it on the next search
• Modal tabs and the similarity threshold: the Semantic settings window has three tabs - Index (target folder, rebuild mode, progress, delete all), Model (Gemini / EmbeddingGemma 2, vector size, Ollama URL, model size, connection test) and Search. On the Search tab you can set a minimum score for similar-image results (e.g. 0.6 shows only images scoring 0.6 or higher), a minimum score for text search, and the maximum number of results. Scores differ by model, so each model keeps its own values; the list header shows the active threshold

Formats & Auto-save

• Workflow auto-save: images generated in the Generate UI tab automatically have their workflow saved to gallery metadata and shown in the JSON tab
• Supports PNG (tEXt/iTXt), JPEG, WebP, GIF, MP4, WebM, PSD, and audio (WAV, MP3, OGG, M4A, FLAC, Opus — waveform thumbnail, built-in player, prompt/workflow tags written by ComfyUI's SaveAudio nodes); workflow extraction reads ComfyUI prompt/workflow keys embedded in PNG metadata (including chunks appended after IEND by ComfyUI-Custom-Scripts), WebP EXIF, or MP4/WebM container tags (as written by SaveVideo, e.g. MiniMax H3 output); the Prompt tab also reads A1111 / Forge / Fooocus parameters text when no workflow is embedded. Audio waveform thumbnails are colored by format (MP3 blue, WAV green, FLAC amber, OGG/Opus purple, M4A rose) so formats can be told apart at a glance; the detail panel shows the waveform with the player below it.
• PSD files: thumbnails and full-size previews show all layers merged together (hidden layers excluded); the underlying PSD file itself is left untouched — only the preview shown in Gallery is a flattened rendering

Browsing

• Browse installed models: Checkpoint, LoRA, VAE, ControlNet, UNET, TextEncoder, Hypernetwork, Embedding with sub-tab switching
• Thumbnail and Table view modes with pagination; Table view shows Type and Base Model columns sourced from CivitAI data alongside filename, subdirectory, and extension; column headers are clickable to sort — click once for ascending (▲), again for descending (▼), a third time to clear the sort; the E/D column sorts by enable/disable status
• Search, tag filter, group filter, favorites filter, and status filter (All / Enabled only / Disabled only)

Side Panel & CivitAI

• Side panel: opens to CivitAI tab by default when a model is selected; Info (file path, tags, memo), Groups management, CivitAI integration
• CivitAI integration: fetch model info by SHA256 hash, batch fetch per model type; the batch fetch reuses saved hashes, imports from existing .metadata.json sidecars and hashes the rest in parallel; 'Skip not found' skips models known to be missing on CivitAI

Apply & Detail

• Detail modal: preview image, CivitAI info (base model, trained words, tags), thumbnail change — upload any image format to replace the preview; changes take effect immediately without restarting ComfyUI; broken/empty preview files are automatically skipped; Delete button permanently removes the model file and all associated sidecar files
• GenUI Model button: apply the selected model to the corresponding node in GenerateUI's current workflow (Checkpoint / LoRA / VAE / ControlNet / UNET / TextEncoder / Hypernetwork); Embedding tab shows GenUI PP / GenUI NP buttons instead — appends (embedding:Name:1.0) to the Positive or Negative prompt of the loaded workflow

Groups & Badges

• Group management: create, rename, delete groups and assign/remove models; Checkpoint and LoRA tabs support B (Batch) and S (Stack) quick-assign buttons per model in both card and table views
• User-defined badges: assign free-label badges with custom colors shared with the Workflow tab; 'Auto badges from CivitAI' in Manage Badges creates badges from CivitAI base models

Enable/Disable & Bulk Operations

• Enable/Disable models: toggle visibility in ComfyUI by renaming file extension (.disabled suffix). Disable per model (⏸ button on each card) or per group (Enable All / Disable All in Group panel). Changes take effect after ComfyUI refresh.
• Multi-select & bulk operations: click Select (green) to enter selection mode, then check multiple models; the bulk action bar is organized into three rows — Group row: select an existing group and Add/Remove, or type a new name and Create & Add; Badge row: select a badge and +Badge / −Badge to apply or remove; File row: select a destination subfolder (or type a new folder name) and Move to relocate model files with all sidecar files (.preview.png, .json, .civitai.info, etc.), Delete Files to permanently remove selected models; header row provides Deselect All and ★/☆ Favorite toggles
• After moving or deleting models, ComfyUI may fail to load them because it caches the old file paths. Perform a Hard Reset from the ComfyUI menu (Queue → Hard Reset) or restart ComfyUI to refresh the model cache.

Tabs Overview

• Open from the Workflow Studio Library button in the ComfyUI toolbar
• Workflows tab: All / ★ Favorites / Groups sub-tabs; ★ shown for favorites in All view
• Nodes tab: All / ★ Favorites / Groups / Sets / 📂 Category / 🧩 Package sub-tabs; Category and Package show a dropdown to filter nodes Alt+click a node to add/remove it from Favorites.
• Models tab: All / ★ Favorites / Groups / By Type sub-tabs
• Prompts tab: browse prompt presets with All/Favorites/Categories sub-tabs

Drag & Drop / Interaction

• Drag & drop workflows onto the canvas to load them
• Drag & drop nodes/node sets onto the canvas to place them
• Drag & drop prompt presets to create WFS_PromptText nodes with positive/negative prompts
• Copy individual positive (P) or negative (N) prompts from sidebar items
• Double-click items to load/place without dragging
• Search within each sub-tab to quickly find items

Information (I) tab

• I tab (Information): drop a ComfyUI PNG/WebP/MP4/JSON to inspect model, LoRA, and prompt metadata in the side panel — sub-tabs: model / lora / Prompts; supports UnetLoaderGGUF, QuadrupleCLIPLoader, Lora Loader (LoraManager), and ImageMetadataLoRALoader node types (API format included); MP4 reads the workflow/prompt tags embedded by SaveVideo, including all-in-one video nodes like MiniMax H3 ImageToVideo
• Information tab — drag items to canvas: model sub-tab places the loader node (Checkpoint → CheckpointLoaderSimple, VAE → VAELoader, Diffusion Model → UNETLoader, Text Encoder → CLIPLoader); double-click also places at canvas center
• Information tab — LoRA sub-tab: drag individual LoRA to place LoraLoader; "Multiple LORA" section at bottom places all LoRAs in a single Lora Loader (LoraManager) node; Prompts sub-tab: drag a prompt to place CLIPTextEncode node with text pre-filled; click prompt to view full text and copy

AI TOOL tab

• AI TOOL tab: Translation, Chat, TOOLS, and Settings sub-tabs powered by Ollama, LM Studio, Lemonade, or Unsloth; Chat supports multi-turn conversations; TOOLS includes VLM image analysis and wildcard generation; settings shared with the SPA AI TOOL tab via localStorage; the Settings sub-tab's VRAM (Ollama) → "Unload all now" unloads every model loaded in Ollama on localhost, decision models included

Customization & Navigation

• ⚙ Theme button (header): customize panel background, text, border colors — saved to localStorage
• Title drag (Send to Canvas): after clicking 'Send to Canvas' (Workflow tab) or 'Copy & Send Canvas' (Gallery tab), the 'Workflow Studio Library' title turns blue with a green ● — drag it onto the canvas to load the workflow; title resets automatically after loading

Layout

4-pane layout — Translation | Chat | TOOLS | Settings — all panes are always visible simultaneously

Translation pane

Translation pane: translate text between Japanese, English, Chinese, or a custom Free language using Ollama, LM Studio, Lemonade, or Unsloth; ⇄ swap button swaps both language selectors and text content; selections are saved automatically

Chat pane

Chat pane: multi-turn conversation with the LLM; Enter to send a message, Shift+Enter for a newline; Clear button resets the conversation history; if the model supports tool calling and asks for an image ("generate a cat picture", etc.) it will run generation on the workflow currently loaded in GenerateUI and show the result inline; the "Allow image generation" checkbox in the pane header toggles this on/off; if an image is attached (dropped in the TOOLS pane) it is sent to the LLM as vision input and, when generate_image is called, used as the base for image-to-image generation instead of text-to-image; generate_image also accepts optional generation parameters the model can fill in from the request — steps, cfg, sampler_name, scheduler, denoise, seed, width, height, batch_size (number of images produced in that one call), and aspect_ratio (a ratio preset like "3:2", applied only if the workflow has a Resolution Selector node feeding width/height — ignored otherwise); anything the model doesn't supply keeps whatever the loaded workflow already has set; models verified to work well for tool calling and vision: Gemma 4:e4b, Qwen 3.5:9b, Ministral 3:3b (Ollama)

Chat pane — SVG generation

Chat pane — SVG: the LLM can also produce SVG graphics directly as text, with no ComfyUI workflow involved; ask it to draw something in SVG and, if the reply contains SVG code, it is rendered inline as a preview with a "Save to Gallery" button that writes it as a .svg file to the Gallery tab's output folder; this does not use tool calling, so it works with any model regardless of tool-calling support

Chat pane — Skills

Chat pane — Skills: pick a skill from the dropdown above the message list to prepend its instructions to the conversation as a system prompt (not shown in the visible chat log); use the pencil button to open the skill manager and create, edit, or delete .md skill files, stored in user/default/Workflow-Studio/ai_skills/; a file's first line block between --- markers can define name/description shown in the dropdown; two starter skills are included by default: "SVG Icon Generator" (decomposes the subject into parts before drawing, for more recognizable SVG output) and "Skill Creator" (interviews you conversationally and drafts a new skill file, ready to save); when a reply contains a ```skill code block, a "Save as new skill" button appears below it that opens the manager with the draft pre-filled

Writing your own skills

Tips for writing your own skills: give a clear frontmatter name/description so it reads well in the dropdown and tooltip; state the exact output format you want and, if there is a deliverable to extract later (like SVG or another skill file), wrap it in a distinctive fenced code block; write concrete, imperative instructions rather than vague ones - smaller local models follow explicit rules and a short worked example far better than general guidance; state hard constraints (forbidden content, security, length limits) explicitly rather than assuming they are implied; when in doubt, select the "Skill Creator" skill in the dropdown and describe what you want - it will interview you and draft the file for you

TOOLS pane

TOOLS pane — VLM: drop an image (PNG/JPG/WebP) and select a task (Describe Image, Create Prompt, Create Tags), click Run; or select "Create wildcards", enter a category name and count to generate plain-text entries one per line; the dropped image is also shared with the Chat pane as its attachment (shown there and used for image-to-image generation) until cleared with the ✕ button

Settings pane

Settings pane: choose backend (Ollama / LM Studio / Lemonade / Unsloth), set API URL, test connection, select model, and use the Unload Model button (next to Test connection) to free the loaded model from VRAM/memory — Ollama unloads every loaded Ollama model, decision models included (the same step as Settings → VRAM Management's "Unload all now"; the Prompt/Tagger settings button does the same), LM Studio uses /api/v1/models/unload, Lemonade uses /api/v1/unload; Unsloth has no unload API, so this shows an unsupported message for it; Unsloth needs either an API key or Keyless API access — set UNSLOTH_API_KEY in a .env file in the plugin folder (copy .env.example) and restart ComfyUI (the key is read server-side and never sent to the browser), or leave it unset and turn on Keyless API access → "Chat and inference" in Unsloth Desktop's Settings → API (requests are then sent without a key; note that setting also opens the API to your private LAN, and keep "Allow tools" off); Unsloth also requires "Auto model switching (OpenAI API)" to be turned ON in the Unsloth Desktop app itself (its own Settings screen) — without it, requests fail with HTTP 404 unless a model was already manually loaded in the Unsloth Studio UI; Unsloth reasoning models return their thinking in a separate reasoning_content field rather than inline <think> tags, so a low Max tokens can make the model spend its whole budget reasoning and return an empty reply — increase Max tokens (2048+) if replies come back blank; Generation section — Thinking mode toggle (off by default; Ollama receives a `think` flag, and regardless of backend any <think>...</think> block is stripped from the output when off, so reasoning models don't clutter Translation/Chat/TOOLS results) and Max tokens (Ollama: num_predict, LM Studio/Lemonade/Unsloth: max_tokens; 0 = unlimited); configure Free language names; Chat Image Generation section lets you enable a dedicated workflow for Chat-triggered text-to-image generation instead of the one currently loaded in GenerateUI; Chat I2I Generation section is the same but for image-to-image generation when an image is attached; settings are shared with the Library panel's A tab via localStorage

Overview & Setup

• Automatic image tagging using WD Tagger (ONNX), SwinV2, DeepDanbooru (.h5), and VLM (Ollama / LM Studio / Lemonade / Unsloth) — 3 sub-tabs: Single / Batch / DB
• Model placement: put each model in its own subfolder under ComfyUI/models/tagger/<model-name>/; the folder must contain a .onnx file + selected_tags.csv (or .h5 + label file for DeepDanbooru)
• Install dependencies into ComfyUI's embedded Python: python_embeded\python.exe -m pip install -r requirements.txt; for GPU ONNX inference install onnxruntime-gpu instead of onnxruntime; TensorFlow (for DeepDanbooru) is commented out by default due to size

Single Tab

• Single tab: drag & drop an image onto the preview area, or click Upload to pick a file; the Tagger button in the Gallery detail panel opens the selected image directly here
• Threshold slider: minimum confidence score for general tags (default 0.35); Character Threshold: separate threshold for character: prefix tags (default 0.85)
• VLM Tagging: enable the checkbox to run a vision model alongside WD Tagger; click the ⚙ Settings button to choose backend (Ollama / LM Studio / Lemonade / Unsloth), URL, model, Thinking mode, Max tokens, and unload the model (with Ollama, every model loaded in Ollama on localhost is unloaded, decision models included) — independent from the Prompt tab's own AI settings; customize the prompt and Max Tags inline; results from both models are merged

Sending Results

• Result tags can be sent to: (1) GenUI:P — appended to the GenerateUI tab's positive prompt textarea and applied to the loaded workflow immediately; (2) Send to Prompt — appended to the Prompt tab's positive textarea; (3) Save to Gallery — saved to Gallery image metadata (requires image opened from Gallery); (4) Write to File — embedded into JPEG EXIF (ImageDescription) or PNG tEXt (Tags key); (5) Save to DB — stored in the internal SQLite database

Batch & DB Tabs

• Batch tab: enter a folder path, configure WD Tagger and enable VLM tagging (uses the same ⚙ Settings as the Single tab); output options: Save to DB (default on), Write to File (EXIF/PNG metadata), Write .txt (creates <filename>.txt alongside each image); click Start Batch to process all images in the folder; progress bar and log are updated in real time; Stop cancels after the current image
• DB tab: searchable database of all tagged images; click a row to open the edit panel and modify WD Tags / VLM Tags; Save updates the record, Delete removes it; Export CSV downloads all records as a CSV file

Overview & Building the Space

• TagSpace places WFS's own data in the EmbeddingGemma 2 vector space and shows it in 3D: Cards (ImagePrompt images with their prompt, shown as thumbnails), Tags (words split out of ImagePrompt prompts, the positive prompts embedded in Gallery images, wildcards, the Tagger DB and the Prompt library, colored by source) and Gallery points (a sample of indexed Gallery images as a faint background, each carrying the tags from its own prompt). Nearby items have similar meanings
• Requirements: Ollama running with EmbeddingGemma 2 (Gallery > Semantic settings > Model). If the Gallery semantic index was made with Gemini, rebuild it with EmbeddingGemma 2 first
• Build / Update: collects the cards, adds card images that are not yet indexed to the Gallery semantic index, reads the positive prompt embedded in each indexed Gallery image (followed upstream from the sampler's positive input, never the negative; cached in tagspace_prompts.json so only new or changed images are read again), embeds new tags with Ollama (cached in tagspace_tags.npz) and projects everything to 3D with PCA. Tags: how many tags to keep — each source is ranked by how many prompts use a tag and the sources take turns, so the many Gallery prompts do not crowd out the other sources; Gallery points: how many Gallery images to show (0 = none). Prompts are split only at commas (and | { } BREAK), not at spaces; long sentences (over 5 words) are skipped. Images and text are centered separately before PCA so cards and their matching tags overlap. The first build took about 2.5 minutes for the cards plus about 3 minutes to read the prompts of 29,000 Gallery images; rebuilds with caches take seconds
• Choosing how many tags: "All tags" uses every candidate tag instead of the Tags number (up to 20,000). "Min uses" drops tags used in fewer prompts than this, counted over all sources — 2 removes one-off typos and fragments. "Wildcards" turns wildcard files on or off as a tag source: words found only in wildcards make up most of the distinct tags (about 37,000 of 47,600 in testing), so turning it off with All tags gives about 10,400 tags (about 6,800 with Min uses 2). The status line shows the number of candidates when only part of them is used. New tags are embedded once (the first build with many new tags takes a few extra minutes)

Choosing Tags & Making a Prompt

• Navigation: drag to rotate, right-drag to pan, wheel to zoom. Hover shows the name, thumbnail and prompt/sources; the checkboxes show or hide Cards, Thumbnails, Tags and Gallery. The source checkboxes (ImagePrompt / Gallery prompts / Tagger DB / Prompt library / Wildcards) show or hide tags by where they came from — a tag stays visible while any of its sources is on and takes the color of its first visible source; hidden tags are also left out of the nearby and search lists. The choices are remembered
• Click a card or tag to select it and list nearby items (clicking only selects — it does not change the prompt). To add it to the Prompt panel, double-click it, press Add next to its name under Selection, or press + in the list (double-click / press again to remove) — cards and tags are ranked separately and listed alternately, so a card also shows its closest tags. Adding a Gallery point adds all tags from that image's prompt as one chip (images without readable tags cannot be added); clicking one lists similar Gallery images (round thumbnails) together with nearby tags and cards; selecting a card or tag, or searching, never lists Gallery images. Use + in the list to add, click a row to move to it. The search box (Enter, any language) places a white marker for the text and lists the nearest items
• Search with a card's or Gallery image's tags: when a card or Gallery point is selected, its prompt tags are shown as buttons (a card's full prompt is under "Full prompt"; card tags appear after Build / Update). Click tags to choose them (click again to deselect) and press "Search with selected" to search the space with those tags joined in prompt order — the same as typing them into the search box. The choice is kept until another item is selected. While tags are selected, the Add button becomes "Add selected (N)" and adds only those tags (in prompt order) as one chip; with none selected it adds the whole item as before. For a Gallery point, "Open in Gallery" opens the Gallery tab with the image's folder selected and the image selected in the list (search and other filters are cleared)
• Prompt panel: a card adds its whole prompt, a tag adds the tag, a Gallery image adds its prompt tags. The text joins them with duplicates removed (case and spacing ignored). "Add to GenerateUI (Positive)" appends it to the positive prompt of the workflow loaded in GenerateUI; Copy puts it on the clipboard
• Tagger fill: about a third of Gallery images have no readable positive prompt (imported or edited images, prompts made only of LoRA tags or long sentences). Choose a Tagger model (ONNX models from the Tagger tab) next to "Tagger fill" to tag those images on Build / Update: "Gallery points only" tags just the sampled Gallery points, "All images without a prompt" tags every indexed image that lacks prompt tags. Default thresholds are used (WD 0.35 / character 0.85, PixAI its recommended values) and rating labels are dropped. Results are cached in tagspace_tagger.json per image and model, so later builds only tag new images; stopping keeps what was done. The tags become the "Tagger fill" source (shown/hidden like the others) and the tags of those Gallery points, marked "(Tagger fill)". The status shows whether the model runs on CUDA or CPU — on the CPU it takes about 0.5 s per image, so check that onnxruntime-gpu is active (see Troubleshooting) before tagging all images
• Display: "Glow" draws points as glowing stars on a night-sky background (dense areas brighten; Gallery points are drawn dimmer so they don't wash out to white) — turn it off for the plain dots and the normal background. "Twinkle" (works with Glow) makes tags, cards and Gallery points slowly twinkle, each with its own rhythm; the selection and nearby highlights stay steady. Hover over the image under Selection or the thumbnails in the Nearby list to see an enlarged preview (clicking a list row changes the selection, so hovering lets you check images first). The Add / Remove button sits on the title row of Selection and stays visible while the text scrolls

Overview

• Layer-based image editor — compose images with multiple layers (Image, Text, Draw, Mask types) and export the composite
• Loading images: drag & drop onto the canvas, File Open button, or send from the Gallery tab via the Image Edit button in the Gallery toolbar; the first image becomes Layer 1 (auto-locked); subsequent images are added as new layers scaled to fit the canvas
• New button: create a blank canvas — prompts for WxH size (e.g. 512x768); clears all existing layers and automatically adds an empty Layer 1
• Open PSD button (next to File Open): loads a layered PSD file from disk and decomposes it into individual layers — position, size, visibility, opacity, and blend mode are restored for each layer; groups and non-raster layers (adjustment layers, etc.) are flattened into their rendered appearance
• Close button (next to Open PSD): closes the current document after a confirmation prompt, discarding all layers and unsaved edits and returning to the empty placeholder view

Tools

• Select (V): click to select a layer; drag to move; drag corner handles to resize; drag the circle above the top edge to rotate; double-click a text layer to re-edit its content; Tool Options bar shows Flip H / Flip V / Rotate field
• Draw (B): freehand brush drawing onto the active draw layer; Tool Options: color, brush size, blend mode; Properties pane includes a MASK EDITOR ONE (COLOR) section for ABR image brushes — always visible, header text is green when brushes are available, gray when none are imported yet; Select is disabled until at least one brush exists
• Text (T): click on the canvas to place a text input overlay; configure font family, size, bold/italic, align, color in the Tool Options bar; click OK to place the text as an exact-size Text layer; double-click an existing text layer with the Select tool to re-edit
• Shape (S): draw geometric shapes onto the canvas; each committed shape becomes an independent draw layer; Tool Options: Shape type (Rect / Ellipse / Line / FreeLine), Rounded checkbox (Rect / Ellipse only), Fill color + None toggle (hidden for Line / FreeLine), Stroke color + width + None toggle (None hidden for Line / FreeLine where stroke is always active), Opacity slider, ↩ Undo button; drag to draw — a blue dashed outline previews the shape; release to commit
• Fill (G): bucket fill — click a contiguous same-color region on the active layer to flood-fill it with a solid color or a linear/radial gradient; Tool Options: Mode (Solid / Gradient), Color (solid) or Shape + Ramp (drag stops to reposition, click a stop then use the color swatch, ＋/－ to add/remove) + Direction dial (drag to set angle/radius, gradient), Tolerance (color-match threshold), Opacity
• Blur (≈): apply Gaussian blur or mosaic to the active layer — whole-layer or region-based (drag a rectangle); see the Blur Tool card below for details
• BG Remove (⬚): remove the background from the active layer using Lightweight (@imgly, runs in browser) or BiRefNet (requires Mask Editor One + birefnet.safetensors in ComfyUI/models/background_removal/); see the BG Remove Tool card below for details
• Mask (🎭): paint masks on a mask layer using 6 sub-tools — Paint (freehand), Color (flood-select by similar color), Alpha (extract from image transparency), Text (stamp text), Vector (Catmull-Rom spline polygon), Shape (rect / ellipse); SAM3 text-prompt segmentation is also available when Mask Editor One is installed; click "Mask" (second row of the Layers header) to add a mask layer; see the Mask Tool card below for details
• Inpaint (🩹): composites the visible layers plus a Mask layer into one RGBA image (mask baked into the alpha channel) and applies it to the first inpaint-capable LoadImage node in the workflow currently loaded in GenerateUI (a node whose MASK output feeds something like VAEEncodeForInpaint); enter Positive/Negative prompts, Grow Mask By (applied to the VAE Encode (for Inpainting) node), and Denoise (applied to KSampler) in the properties panel, then click Run to upload and generate without leaving the Image Edit tab — the result is shown back in the properties panel when done; requires a Mask layer to be painted first and an inpaint-capable workflow loaded in GenerateUI; also works with workflows built around the Mask Editor One custom node (comfyui-mask-editor-one) instead of LoadImage — image/mask are pushed to it via its node_id-keyed server cache and layer_data widget; "Use dedicated workflow" checkbox: when off, the workflow currently loaded in GenerateUI is used (unchanged); when on, pick a saved workflow from the dropdown — it is loaded, edited, and generated entirely in the background without disturbing the workflow shown in GenerateUI

Layer Panel

• Layers are listed from front (top) to back (bottom); click a layer row to make it active
• The Layers header has two rows: the top row has +, ⧉ (Duplicate), −, ↑, ↓; the "Mask" button sits alone on the second row — it adds a new mask layer above the current layer and automatically switches to the Mask tool
• ⧉ (Duplicate layer) button: copies the active layer — including its pixels, position, size, opacity, blend mode, and visibility — and inserts the copy directly above the original as the new active layer; works on any layer type (image, draw, text, mask)
• 👁 / 🚫 button: toggle layer visibility
• 🔒 / 🔓 button: toggle layer lock — a locked layer cannot be moved, resized, or rotated (orange bounding box is shown); Layer 1 is locked automatically when the first image is loaded to prevent accidental moves
• Opacity slider at the bottom adjusts the active layer's transparency
• Type icons: 🖼 = image layer, T = text layer, ✏ = draw layer, ⬚ = mask layer
• Delete key: removes the selected layer (only when 2+ layers exist)

Blur Tool (≈)

• Whole Blur: applies a Gaussian blur to the entire active layer — adjust the intensity slider (1–50 px) and click Apply
• Whole Mosaic: applies a pixelation mosaic to the entire active layer — adjust the block size slider (5–100 px) and click Apply
• Rect Blur: click the toggle to enter rect mode (button turns blue), then drag on the canvas to draw a rectangle — the selected region is blurred on release; adjust intensity before or after enabling the mode
• Rect Mosaic: same as Rect Blur but applies mosaic; preview outline is orange; adjust block size with the slider
• Rect Blur and Rect Mosaic are mutually exclusive — enabling one disables the other; click the active toggle again to exit rect mode
• All operations support Undo (Ctrl+Z)

BG Remove Tool (⬚)

• Model — Lightweight (@imgly): runs entirely in the browser using the @imgly/background-removal library loaded from CDN; no server required; first use downloads the model (~40 MB) and caches it for the session
• Model — BiRefNet: high-quality background removal using the BiRefNet model; requires Mask Editor One to be installed and birefnet.safetensors placed in ComfyUI/models/background_removal/
• New Layer (checked by default): the result is added as a new layer above the active layer at the same position and display size — the original layer is preserved
• When New Layer is unchecked, the active layer's canvas is replaced in-place with the background-removed result
• Click Remove BG to start processing; status text shows Loading model → Processing → Done; supports Undo (Ctrl+Z)

Mask Tool (🎭)

• Add a mask layer: click the "Mask" button on the second row of the Layers panel header; the new mask layer is inserted above the active layer and the Mask tool activates automatically
• Clicking a mask layer in the layer list automatically switches to the Mask tool
• Tool Options bar — sub-tools: Paint / Color / Alpha / Text / Vector / Shape (all work without Mask Editor One) / SAM3 (requires Mask Editor One, disabled if not installed); Invert checkbox inverts the overlay preview; Overlay color picker changes the preview color (default red); Blur slider (0–50 px) softens the overlay edge; the overlay is only shown for the currently active mask layer — inactive mask layers stay hidden until selected
• Properties pane — Paint mode: Mode (Add / Erase), Size (1–200 px), Hardness (0–100%); MASK EDITOR ONE section (always visible — header text is green when ABR brushes are available, gray when none are imported yet): Select button opens the ABR brush library (disabled until at least one brush exists) — choosing a brush replaces the default circle brush; ✕ clears the brush back to Circle; when an image brush is active, Hardness is disabled and additional controls appear: Spacing (stamp interval 5–100%), Angle (rotation 0–359°), Sz Jitter (random size reduction per stamp 0–100%), Rot. Jitter (random rotation per stamp on/off)
• ✂ button on a mask layer row: toggles the layer as a clipping mask — when enabled (blue), the mask clips the layer directly below it so only the painted area is visible; clipping is applied when saving PNG / Gallery / ComfyUI
• SAM3 (Mask Editor One required): text-prompt segmentation powered by the SAM3 model; enter a description of the object to segment (e.g. "cat", "person"), set Max (maximum mask candidates: 3/6/9/12), then click Segment
• SAM3 workflow: after Segment, candidate masks appear as thumbnails in the Properties pane — click to select (blue border + ✓); multiple masks can be selected; click Apply Selected (N) to apply them all; Mode (Add / Erase) controls how masks are merged into the current mask layer; a new mask layer is created automatically if the active layer is not a mask
• ABR Brush Library (Mask Editor One required, Paint mode only): click Select in the MASK EDITOR ONE section to open the brush picker — browse folders on the left, click a thumbnail to apply; "Round Brush (default)" restores the circle brush; brushes are shared with Mask Editor One and stored in its brushes/ folder
• Color sub-tool: click anywhere on the canvas to flood-select pixels similar in color to the clicked point — Properties pane: Mode (Add / Subtract), Tolerance (0–255, color similarity threshold), Feather % (0–100, soft edge falloff within tolerance range)
• Alpha sub-tool: extract the transparency of the image layers as a mask — Properties pane: Threshold (pixels with alpha ≥ threshold become full mask; 0 = all alpha included), Invert (reverse the extracted result), Extract Alpha button applies the operation; works on a composite of all visible non-mask layers
• Text sub-tool: click on the canvas to open a text stamp overlay; enter text, configure Font / Size / Bold / Italic / Align, choose Mode (Add = white stamp / Erase = cut mask), then click Stamp or press Ctrl+Enter; multi-line text supported (newline in textarea)
• Vector sub-tool: click to place control points connected by a Catmull-Rom spline; click the first point again (or press Enter) to close and fill the polygon; Backspace removes the last point; Esc resets all points; Properties pane shows current point count and Mode (Add / Erase)
• Shape sub-tool: drag to draw a rectangle or ellipse mask; hold Shift for a perfect square or circle; a blue dashed outline previews the shape while dragging; Properties pane: Mode (Add / Erase), Shape (Rect / Ellipse)
• Edit in Mask Editor One (Paint mode only): click "Edit in Mask Editor One →" in the MASK EDITOR ONE section to send the current canvas composite — plus the active mask layer's content, if one is selected — to a MaskEditorOne node on the ComfyUI canvas (the currently selected node if it is one, otherwise the first MaskEditorOne node found in the graph) and open its full editor (SAM3, BiRefNet, shapes, etc.) in the ComfyUI browser tab; after clicking Apply there, the result is imported back here as a new mask layer; requires Workflow Studio to have been opened from ComfyUI's top menu button so the ComfyUI tab is reachable, and at least one MaskEditorOne node to exist in the ComfyUI graph

G'MIC Filter (Edit with G'MIC)

• Applies G'MIC-Qt filter effects to the active image layer; the result is loaded back as a new layer
• Click "Edit with G'MIC" in the toolbar to launch G'MIC-Qt GUI with the current layer image
• In G'MIC-Qt: choose a filter, adjust parameters, then click OK — a "G'MIC-Qt filter output" window appears; close it to save and return the result to the Image Edit tab
• Requires G'MIC-Qt Standalone to be installed and its path configured in Settings → G'MIC-Qt Executable Path; only image-type layers are supported

G'MIC-Qt Installation

• Download G'MIC-Qt Standalone from gmic.eu/download.html — choose the "G'MIC-Qt" package for your OS (Windows: gmic_qt-win64.zip)
• Extract the zip to any folder (e.g. C:\tools\gmic); no installer required
• Open Settings → G'MIC-Qt Executable Path, enter the full path to gmic_qt.exe (e.g. C:\tools\gmic\gmic_qt.exe), then click Save

Text Object Quality

• Text layers are sized exactly to the measured text bounding box — no extra whitespace
• When a text layer is resized with the Select tool, the canvas is regenerated at the new display size so the text remains sharp (no blurring)
• Re-editing a text layer (double-click) resets it to native size; re-scale afterward if needed

Export & Navigation

• Save PNG: composites all visible layers and downloads the result as a PNG file
• Save to Gallery: prompts for a filename (default: wfs-image-YYYYMMDDHHmmss) and saves the composite PNG directly to the Gallery root folder (configured in Settings > Gallery Output Folder); requires the Gallery tab to have been opened at least once to set the root
• Save PSD: downloads a layered PSD file with every layer preserved separately — position, rotation, flip, and scale are baked into each layer's pixels (PSD layers cannot store a rotation angle), while opacity, blend mode, and visibility are kept as real, editable PSD layer attributes; clipping masks are merged into their target layer since PSD's native layer-mask mechanism is not used
• Send to Workflow: uploads the composite PNG to ComfyUI's input folder via /upload/image and writes the resulting filename into the image widget of the currently selected node in the ComfyUI graph, falling back to the first LoadImage-type node found; requires Workflow Studio to have been opened from ComfyUI's top menu button so the ComfyUI tab is reachable
• Canvas navigation: scroll wheel to zoom, Space + drag to pan
• Undo / Redo: Ctrl+Z / Ctrl+Y (or toolbar buttons ↩ ↪)

Image Edit Keyboard Shortcuts

• V: Select tool
• B: Draw tool
• T: Text tool
• S: Shape tool
• G: Fill tool
• Delete: Delete selected layer (requires 2+ layers)
• Ctrl+Z / Ctrl+Y: Undo / Redo
• Space + drag: Pan canvas
• Mouse wheel: Zoom in / out
• Double-click (Select tool on text layer): Re-edit text

• Plan subtab: the topbar's settings row holds Aspect Ratio / Megapixels / Multiple / Duration (seconds) / Noise Seed as this plan's base settings — Duration always reflects the currently selected block (each block keeps its own value), the rest are plan-wide. A second row below adds Width / Height / Turbo Mode / Strength / Steps / Prompt Enhance, each enabled only for workflows that actually support it (see helpVideo2). Split the timeline into blocks with the ＋ Split / ＋ Block / Delete buttons — each block has its own Prompt, Duration, and First/Last Image — First Image can be None, an explicit image, or "use previous block's last frame" (an explicit Last Image on the previous block always wins over extracting one from its generated video). Click Run to generate every block in order; Pause/Cancel work mid-run.
• A plan with a single block behaves exactly like the old one-shot form. Model selection (UNet / CLIP / VAE / Audio VAE) is fixed to the loaded workflow's defaults. For workflows with no ResolutionSelector node (e.g. Wan2.2, LTX-2.5 First & Last Frame to Video), the Aspect Ratio / Megapixels / Multiple fields are disabled and the workflow's own Width / Height become directly editable instead. Turbo Mode / Strength / Steps only apply to MiniMax H3's turbo LoRA, and Prompt Enhance only to LTX-2.5 — both stay disabled for other model families. Noise Seed is disabled for the one workflow that doesn't expose it: Wan2.2 Text-to-Video.
• Use the "Load in Video" button in the Workflow tab's detail modal to load a workflow containing a MiniMax H3 Image-to-Video node, an LTX-2.5 Text/Image/First&Last-Frame-to-Video node, a Wan2.2 Text-to-Video node, or a FastH3 OmniRef (MiniMax H3 Reference-to-Video) node — for FastH3 / Pika-H3-Flex the First Image and Last Image fields become Reference Image (ref_image_0) and Reference Image 2 (ref_image_1); leaving either one empty (None / Clear) disconnects that reference input even if the workflow had an image wired to it; Reference Image 2 is never used as the previous block's last frame for "Use previous block's last frame" (the actually generated last frame is used instead) — this starts a fresh single-block plan seeded from the workflow's own current values. Unsupported workflows show an error instead.
• Generated videos (mp4) automatically appear in the Asset subtab's Video Temp group, and can also be browsed and played back in the Gallery tab. Organizing keepers into Video Assets is entirely up to you, on your own schedule.
• The center panel shows two previews: the left one shows either the video you select in the Asset subtab or whatever you drop/pick in the Video Source panel on its left (Clear resets it to empty; "Register as Asset" copies the loaded video into the output folder and tags it into Video Assets so it shows up in the Asset subtab), letting you use the Frame/GIF tools without running the loaded video workflow first; the right one always shows the most recently generated clip.
• Frame tab (right panel): play/seek the preview video to the position you want, click Capture Frame to grab that frame client-side, then Save to Output to write it as a PNG into ComfyUI's output folder — check "Add to Video Assets group" first to also tag the saved frame into Gallery's Video Assets group.
• GIF tab (right panel): set Start/End (seconds), FPS, and an optional Max Width, then Convert to GIF — the server decodes the video and encodes an animated GIF into ComfyUI's output folder.
• Chaining: setting a block's First Image to "use previous block's last frame" continues smoothly from the previous clip — if that previous block has its own explicit Last Image, that image is used directly; otherwise the actual last frame of its generated video is extracted automatically.
• Project tab (sidebar): lists saved Video Plans while the center Plan subtab is active, or saved Edit projects while the center Edit subtab is active (thumbnail/block or clip count, last updated) — click one to load it, or delete it with the × button; clicking the same tab again collapses the panel.
• Highlight color: the Prompt / Duration / First Image / Last Image / Aspect Ratio / Megapixels / Multiple / Noise Seed / Width / Height / Turbo Mode / Strength / Steps / Prompt Enhance labels turn the same highlight color as the GenerateUI Model tab (customizable in the Settings tab) when the loaded workflow actually supports that field — e.g. for a Wan2.2 workflow (no ResolutionSelector node), the Aspect Ratio / Megapixels / Multiple labels stay unhighlighted while Width / Height light up instead.
• Edit subtab: a lightweight clip timeline for trimming and concatenating video/image clips outside of generation. Add clips via the Video Source panel's "Add to Edit" button or the Asset subtab's "Send to Edit" button, then drag blocks to reorder (or use the ◀/▶ toolbar buttons), Duplicate/Delete the selected clip, and Clear to empty the timeline (this also resets the Audio section). The trim panel for the selected video clip shows a time ruler, a draggable playhead synced to the Source preview, and draggable in/out handles with time badges — image clips instead get a simple hold-duration field. ▶ Preview plays every ready clip back-to-back (trimmed to its in/out points) in the right-hand result preview; Export builds and runs the actual ComfyUI graph (trim → concatenate if more than one clip → save), tagging the result into the Video Temp group automatically. The Audio section of the export panel controls the soundtrack: "Keep original audio" (with its own volume in dB) keeps each clip's audio aligned to its segment even across multiple clips (image clips contribute silence), and "BGM..." lays one audio file over the whole video with its own volume and start offset (a longer BGM is cut to the video length). Each clip can also carry text overlays ("+ Add text" under the trim panel: text, start/end seconds within the clip, size as % of frame height, color, 9-position anchor, outline, background box); they are previewed live over the Source/Result panes and burned in on Export as a final pass. The BGM can be chosen with "BGM...", by dropping an audio/video file onto the Audio section, or with "Set as BGM" on a video in the Asset subtab (its audio track is used). Video clips can also be cropped: "Edit crop" shows a draggable/resizable rectangle over the Source preview (optionally locked to 16:9 / 9:16 / 1:1 / 4:3 / 3:4) — "Done" keeps it, "Cancel" restores the crop from before editing, and switching to another subtab/tab ends editing like Done; the export size becomes the first video clip's cropped size, and other clips of a different size are center-fit to it. The "Convert audio..." button next to the crop buttons converts the selected video clip's audio track to FLAC / MP3 / Opus / M4A / WAV (same dialog as Gallery's Convert) and saves it into the output/video folder. ↶/↷ in the timeline toolbar (or Ctrl+Z / Ctrl+Y) undo and redo edits to clips, trims, crops, text and audio settings. The export panel's Save/Save As/Load buttons persist the timeline itself (clip order, trim points, crop, text overlays, audio/BGM settings, and which uploaded file each clip and the BGM refer to) as a JSON project file on the server. The project only stores references to those files in ComfyUI's input folder, so Load re-fetches each clip from its saved server reference and re-probes it — the original files must still exist (Settings → Full Backup can bundle them with "Include media used by Video Edit projects"). These saved projects also show up in the sidebar's Project tab whenever the Edit subtab is active (see the Project tab item).
• Asset subtab (center panel, next to Plan/Edit): browses every video/image tagged into Video Assets or Video Temp (via the group dropdown, or "All Video Assets" for both). Search filters by filename; the ▦/☰ buttons switch between a thumbnail grid and a table (filename/updated/tags). Selecting an item shows its tags/memo, loads it into the center preview, and offers "Send to Edit" (queues it as a clip in the Edit subtab) plus, for images only, "Set as First Image"/"Set as Last Image" (uploads it straight into the currently-selected Plan block, switching to the Plan subtab). Audio files tagged into Video Assets also appear ("Audio Only" filter): the detail panel gets a player plus "Set as BGM" and "Add as sound" (places it on the Edit subtab's Audio track at the selected clip's start).

General

• Escape: Close modal/panel
• Enter: Confirm rename, send chat
• Shift+Enter: New line in chat
• Double-click: Open detail modal

Image Edit Tab Shortcuts

• V: Select tool
• B: Draw tool
• T: Text tool
• S: Shape tool
• G: Fill tool
• Delete: Delete selected layer (requires 2+ layers)
• Ctrl+Z / Ctrl+Y: Undo / Redo
• Space + drag: Pan canvas
• Mouse wheel: Zoom in / out

Connection Issues

• Cannot connect to ComfyUI: Check if ComfyUI can generate images, verify URL in Settings, try refreshing or restarting
• Cannot connect to Ollama: Use connection test button, check if Ollama is running and models are downloaded

Workflow & Generation Issues

• Workflows not showing: Click refresh button, check if loadable in ComfyUI, try restarting browser/ComfyUI
• Image generation fails: Check if specified models exist in ComfyUI, verify connection, try restarting
• LoRA Stack fails with "No such file or directory" error: The LoRA may not be recognized by comfyui-lora-manager (known issue). Try a different LoRA or check if the file appears in Lora Manager's own UI
• Model loading error after moving or deleting models: ComfyUI caches file paths and may still reference old locations. Perform a Hard Reset from the ComfyUI menu (Queue → Hard Reset) or restart ComfyUI to clear the cache.
• Generate runs a different workflow than the one just loaded: a Batch type checkbox (Checkpoint/LoRA/Prompt/Workflow/Sampler/Scheduler) is left ON in the Batch subtab. While any Batch type is active, the Generate button runs the batch selection instead of the currently loaded workflow. Open the Batch subtab and turn off the active batch type checkbox.

Tagger & Model Issues

• Tagger tab shows no models: verify the model folder exists at ComfyUI/models/tagger/<model-name>/ and contains a .onnx or .h5 file; if onnxruntime is not installed, run: python_embeded\python.exe -m pip install onnxruntime
• Model tab shows a checkpoint you didn't expect (e.g. always the same model regardless of the loaded workflow): the checkpoint saved in the workflow file is not installed, so it was silently replaced with another available model during loading — an error toast reports the original (missing) model name when this happens. Select the correct checkpoint manually in the Model tab, or enable "Default Checkpoint" in Settings to force a known-good model on every load.

Semantic Search (Gallery)

• EmbeddingGemma 2 says 'Cannot reach Ollama' or 'not downloaded': start Ollama (it must be running while indexing and searching) and check the Ollama URL in Semantic settings > Model; download the model with 'ollama pull embeddinggemma-2:740m' (or embeddinggemma-2:440m). If indexing fails now and then with 'connection was forcibly closed' errors, security software that filters per-app traffic (e.g. AdGuard) may be interrupting ollama.exe - exclude Ollama from filtering. Failed requests are retried automatically; images that still fail are counted as failed and are picked up again by the next 'New / changed images only' run
• Semantic Search with Gemini says 'GEMINI_API_KEY is not set' or the key is rejected: add GEMINI_API_KEY=your-key (no leading #) to the plugin's .env file (copy .env.example), then restart ComfyUI - the .env file is only read at startup. Get a key at Google AI Studio. If you do not want to use the API, choose EmbeddingGemma 2 (Ollama, local, no key) in Semantic settings > Model
• Semantic Search or Similar shows no results: results only include images that are already indexed inside the selected folder (a green dot in the folder tree means the folder is fully indexed) - build the index from the gear button first, and select a folder that contains indexed images. After changing the model, vector size or image precision, choose 'Rebuild all'. A minimum score set in Semantic settings > Search can also hide everything; set it to 0 to check. The first search after indexing takes a few seconds because the local model is reloaded