--- name: upscale-film-still description: Upscale a film still, screenshot or small reference with Magnific Precision V2 sublime — 2× with a grainy analog look by default, 4× only when the size is needed; it cleans noise and blocks, keeps faces and the lens look, invents nothing. --- # Upscale a film still or small reference FlashBoards user skill, version 1.2.3 (2026-10-13). On the board, read these guides with `list_skills` and `get_skill` when the assistant exposes them; otherwise use the hosted index through an available read-only retrieval tool. Use that runtime’s actual model discovery, current page context and guarded board actions for execution. Keep native readiness, approval and cost gates; do not claim a guide was read when retrieval is unavailable. Read related guides with `get_skill({skillId:""})` or the [hosted index](https://pub-78da82d51ed14147ac554d38094b0c0b.r2.dev/user-skills/1.2.3/index.html). Reading a guide does not start or authorize a paid generation. Read `upscale` for the shared rules. ## Choose Default: `enhance_media` with `modelId: "magnific-precision-v2"`, `flavor: "sublime"`, `ultraDetail: 100`, `scaleFactor: 2`, `sharpen: 5`, `smartGrain: 12` — the best look in the tests. 4× only when the size is needed (it looks worse). The price steps up with the output size: quote first with `estimate_media_enhancement_cost`. On film stills of about 1000 × 580 at 4× every face was kept. A sharper setting brings out pores, lashes, single hairs and metal and adds texture to backgrounds; a softer one stays closer to the source. What it does: noise and JPEG blocks gone; hair, knit, sand and paintings resolved; faces unchanged; **out-of-focus areas stay out of focus**; tiny far figures stay tiny — nothing is invented. ## Steps 1. Take the largest source available — a film frame from `search_movie_frames` is a WebP preview: make it an image of the account first with `crop_image` of the whole frame (`source: {previewHandle}`, x 0, y 0, width 1, height 1) and enhance that; a frame of one of the person's videos comes from `extract_video_frame`. 2. Quote, then `enhance_media` → `get_media_enhancement`. 3. Compare at full size, not the whole picture shrunk: `crop_image` the same region (the same fractions) from the source and the result, `arrange_images` the two crops side by side, then `describe_media` the pair with a question ("Same faces? Anything invented? Is the lettering the same?"). ## Never - Expect it to fix focus or motion blur — it keeps the lens look. - High creativity on the Creative upscaler on faces of real people — it changes who it is. - Image models as upscalers on a real face: GPT Image 2.5 redraws (cooler colour, deeper lines, painted skin at 4K), Nano Banana 2 invents veins, spots and stubble. Only the faithful upscale kept the person. - A smaller input is fine: the same still at half size through 4× was as sharp at the same viewing size, only half as big. ## Execute through MCP or on the board Use the person's FlashBoards account; never ask for a personal provider key or run the source's local scripts. Discover `get_account`, `list_generation_models` and the tools of this client first: a published guide does not prove a feature is deployed. **Headless, no open board.** Quote with `estimate_generation_cost` (skill models: `estimate_skill_model`), then run `generate_image`, `generate_video`, `generate_audio` or `run_skill_model` with one stable `generationAttemptId` per logical attempt. Pass `maxCostUsd` only when the current operation and selected model support it; otherwise use the quoted cost and the person's explicit approval with the supported controls. Never silently ignore an unsupported spending cap; make one `get_generation` check after `retryAfterSeconds`. Pass the person's own results by `generationId`: images in `referenceGenerationIds`, `firstFrameUrl` and `endFrameUrl`, audio in `referenceAudioUrls` or `targetAudioUrl`, videos in `referenceVideoGenerationIds`. They are read on the server; signed result links do not work as public URLs. Every `generationId` a tool returns stays valid: a later read of the same result gives a different string, and both work. Film frames and gallery pictures go in by `previewHandle`: `referencePreviewHandles` of the generation tools, a `{previewHandle}` source of `arrange_images`, `crop_image` and `pad_image`, and `describe_media`. New files come from `show_media_upload_picker` as receipts. The person's character comes in as its sheet, by `generationId` or as an upload; there is no search by name. If the person names a character without the sheet, ask for it or make one with `character-sheet`; do not scan recent results for it. Free server steps: `trim_video`, `concat_videos`, `conform_video`, `replace_video_audio`, `extract_video_frame`, `extract_video_audio`, `detect_video_cuts`, `crop_image`, `pad_image`, `arrange_images`, `cut_audio_span`, `concat_audio_tracks`, `mix_audio_tracks`, `fit_audio_duration`, `add_audio_reverb`. Check every result with `describe_media` (a question about an image; `model`, `mode` and `sourceRange` only for a video) and `transcribe_media` for speech. Both checks are paid: `describe_media` costs a fraction of a cent for an image and about 2–4 ¢ for a short video (more for a long one), `transcribe_media` under 1 ¢ a minute — count the checks you plan in the price you name before the first paid step. `describe_media` is not reliable about sound: it misses effects mixed under music and can hear voices or instruments that are not there. Check speech with `transcribe_media` and ask the person to listen for effects and music. Never repay an uncertain submission; reuse an attempt ID only for the identical request. Make each new `requestId` or `generationAttemptId` unique, for example the task, the date and a short random suffix: an ID used before, even in another chat, replays that earlier request or answers `REQUEST_ID_CONFLICT`. **On the board.** Inspect with `list_board_sessions` and `get_board_snapshot` and carry the same `sessionId` and a fresh `activeBoardId` as `expectedBoardId`. Native cards: `execute_board_action` (`listNativeModels`, `setModel`), `prepare_board_generation` with ordered board items or owned outputs, then one `generate_on_board` within the authorized budget. Board media tools: `list_media_tools` → `start_media_tool` → `get_media_tool_run`. Put headless results on a board with `add_media_to_board`. Keep mandatory safety settings and the live limits of each model. Prices, timings, endpoints and "free retry" claims in the sources are historical, not FlashBoards contracts. If a step this guide needs is not available or is refused (a tool error, `audio_not_configured`, a missing model or input), keep the finished assets, tell the person which step is blocked and why, and ask how to go on. A single generation that ends `failed` is not a blocked step: submit it once more with a new `generationAttemptId` (reworded if it may have hit the content checker), and stop to ask only if it fails again. A failed attempt is not always refunded, so the retry may be paid again and `maxCostUsd` caps each request on its own: count both against the budget the person approved. Never swap in another route on your own: no image model redrawing a layout or a frame, no `describe_media` in place of the frames it should check, no clip generated only to take its sound, no picture drawn where the guide takes a film frame. ## Source and related guides - [Original Learn guide](https://flashboards-h01.vercel.app/learn/post-production/ai-upscaling/skills/upscale-film-still.md) - Updated from the owner's skill sources of 2026-10-11. Read: `upscale`, `upscale-closeup`, `filmscene`. Source experiments and demo materials are historical; use the person's own approved media.