--- title: "Topaz Image Upscale AI Upscaler | Made" description: "Upscale images 2x or 4x with Topaz Labs precision models in Made. See original before/after examples, recovered detail, pricing, and limits. On Made: 0.8 credits / image." url: https://www.made.app/models/topaz-upscale-image --- ![Portrait upscaled to 2896×2172 with Topaz Image Upscale in Made](https://www.made.app/images/models/topaz-upscale-image/portrait-2x.jpg) [Models](https://www.made.app/models) / Topaz Image Upscale ![1448×1086 source portrait before upscaling](https://www.made.app/images/models/edit-sources/window-portrait.png) Before Topaz Labs · image model # Topaz Image Upscale Upscale images 0.8 credits / image · every plan · [price breakdown](https://www.made.app/price-sheet/topaz-upscale-image) · [API playground](https://www.made.app/playground/topaz-upscale-image) [Upload a photo](https://www.made.app/tools/ai-image-generator?model=topaz-upscale-image) Add the image to upscale and pick 2× or 4× — no prompt needed. Made with Topaz Image Upscale · Portrait at 2× Topaz Image Upscale runs Topaz Labs’ precision upscaling models — the professional standard for enlargement — recovering real detail at 2× or 4× from a single input image, no prompt required. Original results ## Topaz Image Upscale examples made in Made These examples use media produced for Made. Prompts are included when the production record allows them. Input Output ### Portrait at 2× Input ![Heavily compressed 362×272 product photo before upscaling](https://www.made.app/images/models/topaz-upscale-image/low-res-source.jpg) Output ![Low-resolution product photo rescued at 4× with Topaz Image Upscale in Made](https://www.made.app/images/models/topaz-upscale-image/low-res-4x.jpg) ### Low-res rescue at 4× Input ![1448×1086 source interior before upscaling](https://www.made.app/images/models/edit-sources/living-room.png) Output ![Interior photograph upscaled 2× with Topaz Image Upscale in Made](https://www.made.app/images/models/topaz-upscale-image/interior-2x.jpg) ### Interior at 2× ![Close crop of the 2× portrait output showing recovered skin and hair detail](https://www.made.app/images/models/topaz-upscale-image/detail-portrait.jpg) ### Recovered detail: skin and hair ![Close crop of the 2× interior output showing recovered texture and edges](https://www.made.app/images/models/topaz-upscale-image/detail-interior.jpg) ### Recovered detail: texture and edges ![Close crop of the 4× rescue output rebuilt from a 0.1-megapixel input](https://www.made.app/images/models/topaz-upscale-image/detail-low-res.jpg) ### Recovered detail: 4× from 0.1MP ## Where Topaz Image Upscale fits best ### Best uses - Enlarging images to print or hero-banner resolution - Rescuing small, web-compressed photos at 4× - Sharpening AI generations before delivery - Detail recovery that stays faithful to the source ### Limits to know - It is billed by output size — 0.8 credits for every started 24 megapixels of output — so a 4× pass on a large input costs more than the same pass on a small one; Made quotes the exact price before generation. - It enlarges and restores; it cannot invent content outside the frame — use an image extender for outpainting. ## Specifications in Made These are the controls exposed by Made, which may be narrower than a provider’s full API. **Aspect ratios** Matches the input image **Resolution** 2× or 4× the input, billed per started 24MP of output **Duration** Not applicable **Output formats** JPEG **Reference images** 1 **Processing** Single-pass upscaling; progress appears in the generation view. ## How to use Topaz Image Upscale in Made 1. **Add the image** Upload the photo or generation to enlarge — there is no prompt to write. 2. **Pick the factor** Choose 2× for finished images or 4× for small, low-quality sources. 3. **Check the quote** Cost scales with output megapixels; Made shows the exact price before you run it. 4. **Download the master** The output keeps the input’s framing at the new resolution, ready for print or delivery. Capabilities reviewed 2026-09-03 · Provider: [Topaz Labs](https://fal.ai/models/topaz/upscale/image/precision) Made shows the price in credits before generation. [View Made pricing](https://www.made.app/pricing) ## Go deeper on Topaz Image Upscale ### [Topaz Image Upscale pricing](https://www.made.app/price-sheet/topaz-upscale-image) 0.8 credits / image — the full breakdown, verified. ## Compare relevant models video ### [SeedVR2 Video Upscale](https://www.made.app/models/seedvr-video-upscale) SeedVR2 is ByteDance’s video restoration model, upscaling any clip 2× or 4× with temporal consistency — frames stay coherent instead of flickering — from a single video input, no prompt required. image ### [Restore Image](https://www.made.app/models/restore-image) Restore Image is a focused Made workflow for reducing scratches, fading, and visible damage while preserving the recognizable people and composition in a source photo. image ### [Seedream 5 Pro Edit](https://www.made.app/models/seedream-5-pro-edit) Seedream 5 Pro Edit is the editing tier of ByteDance’s flagship Seedream 5 Pro, changing only what you ask — backgrounds, colors, objects, wardrobe — while preserving everything else, with up to 10 reference images per request. ## Continue with a related tool ### [Image Upscaler](https://www.made.app/image-upscaler) Enlarge photos 2× or 4× with Topaz and get the detail back, or upscale video with SeedVR2 or FLUX 3. Drop a file to see the exact price before you pay. ### [AI Photo Editor](https://www.made.app/ai-photo-editor) Skip the complex menus and toolbars. Edit Images With Text Prompts. Our AI photo editor understands what you want. Type "remove the background" or "make it brighter" and watch it happen instantly. ### [Expand Image](https://www.made.app/expand-image) Extend any photo beyond its edges. Pick a new aspect ratio or zoom out, and AI fills in the scene around your original photo. Questions, answered ## Topaz Image Upscale FAQ Need a specific answer? [Contact support](mailto:support@made.app) ### What is Topaz Image Upscale? It runs the precision upscaling models from Topaz Labs — the company behind Gigapixel, the long-standing professional standard — enlarging images 2× or 4× while recovering real detail. ### How is it priced? By output size: 0.8 credits for every started 24 megapixels of output, where output megapixels are the input size times the square of the factor. The same rate applies to every precision sub-model, and Made quotes the exact cost before generation. ### Does it need a prompt? No. The image is the only required input — just pick the upscale factor. ### What is the difference between 2× and 4×? 2× doubles each dimension and suits already-decent images; 4× quadruples them and is built for small or degraded sources. Because billing follows output size, 4× on the same input costs up to four times as much. ### Can it upscale video? No — it is image-only. Use SeedVR2 Video Upscale for temporally consistent video upscaling. ### When should I choose another model? Choose Restore Image when damage — scratches, fading, noise — is the main problem, or an edit model like Seedream 5 Pro Edit when you need to change the image, not enlarge it. --- Markdown version of https://www.made.app/models/topaz-upscale-image. Every public Made page has one at its URL plus .md (https://www.made.app/models/topaz-upscale-image.md). Site summary for AI assistants: https://www.made.app/llms.txt