# Topaz Gigapixel v1.1.0 - v1.1.1 **URL:** \ **Category:** Releases\ **Created:** [January 23, 2026, 2:00am UTC](https://community.topazlabs.com/t/topaz-gigapixel-v1-1-0-v1-1-1/100363 "2026-01-23T02:00:27Z")\ **Posts on this page:** 20\ **Page:** 1
**Author:** ![esther.huynh](https://community.topazlabs.com/user_avatar/community.topazlabs.com/esther.huynh/32/211052_2.png) [@esther.huynh](https://community.topazlabs.com/u/esther.huynh)\ **Post date:** [January 23, 2026, 2:00am UTC](https://community.topazlabs.com/t/topaz-gigapixel-v1-1-0-v1-1-1/100363/1 "2026-01-23T02:00:27Z")
Hello! Today we’re excited to release **Topaz Gigapixel v1.1.0** , an update focused on expanding our **generative model lineup** , refining the **Cloud rendering workflow** , and delivering a number of important fixes and quality-of-life improvements. Thanks again for being part of the Topaz Gigapixel community 💙 As always, we’d love to hear your feedback. Esther H. Topaz Labs * * * **Topaz Gigapixel v1.1.1** Windows: [[Download]](https://downloads.topazlabs.com/deploy/TopazGigapixel/1.1.1/TopazGigapixel-1.1.1.msi) Mac: [[Download]](https://downloads.topazlabs.com/deploy/TopazGigapixel/1.1.1/TopazGigapixel-1.1.1.pkg) Snapdragon: [[Download]](https://downloads.topazlabs.com/deploy/TopazGigapixel/1.1.1/TopazGigapixel-arm64-1.1.1.msi) **Released on January 23, 2026** * * * Topaz Gigapixel v1.1.0 Windows: [[Download]](https://downloads.topazlabs.com/deploy/TopazGigapixel/1.1.0/TopazGigapixel-1.1.0.msi) Mac: [[Download]](https://downloads.topazlabs.com/deploy/TopazGigapixel/1.1.0/TopazGigapixel-1.1.0.pkg) Snapdragon: [[Download]](https://downloads.topazlabs.com/deploy/TopazGigapixel/1.1.0/TopazGigapixel-arm64-1.1.0.msi) Released on January 22, 2026 * * * ## Wonder 2 — Precision Detail Without the “AI Look” (Cloud Only) **Wonder 2** is an evolution of the original Wonder model, redesigned to focus on **precision and realism** —especially in faces, skin textures, and fine surface detail. ![Wonder comparison](https://community-cdn.topazlabs.com/original/3X/c/f/cf61dcf6ddbc0fd3fd7bab0fb9e9beaa9f717b63.jpeg) The goal with Wonder 2 is to aim for: - Restore fine facial and texture detail - Recovers text, logos, and signage - Reduce artificial-looking patterns - Minimize generative artifacts - Improve overall quality compared to Wonder 1 ![Image by Robert Anasch](https://community-cdn.topazlabs.com/original/3X/a/6/a6bded1d8fdaa7b3c50c32246cb90cb4073ef664.jpeg) **Key things to know** - **Cloud render only for Topaz Gigapixel** - Single-step model with **no preview controls** - Best results when upscaling **4×** - Not recommended for **low-light phone images with heavy noise** _ **Wonder 1 vs Wonder 2 results & false resolution** _ _If you’ve experienced getting good results with Wonder 1 but not with Wonder 2, there is a chance your image may have false resolution_. This is common with images from scanners, screen captures, or online sources. False resolution happens when an image is upscaled—its pixel dimensions are increased without adding real detail. The image looks large, but the extra pixels are interpolated and don’t contain true information. _You can spot false resolution by viewing the image at 100% (actual size). If you see compression blocks, pixel stepping, or artifacts in areas that should be smooth, the image likely has false resolution._ **Workaround:** _Try downscaling the image first. Downscaling can be done in a different image editor. Downscaling removes excess fake pixels and condenses the real detail, which often leads to clearer results when processing the image in Topaz Gigapixel with Wonder 2._ * * * ## Recover 3 — Our Most Natural Enhancement Model Yet **Recover 3** is built for users who want **soft, realistic enhancement** rather than aggressive detail reconstruction. It shines especially with: - Fur and feathers - Natural textures that benefit from subtle recovery Unlike Wonder 2, Recover 3 is designed to be a **general-purpose enhancement model** rather than a precision generative tool. ![Recover 3 Comparison](https://community-cdn.topazlabs.com/original/3X/9/6/964b3e75d886930a8bd365f8d71fb40b32cd7858.jpeg) ![Recover 3 Comparison - zoomed in](https://community-cdn.topazlabs.com/original/3X/d/9/d98da9053c36d6e4ce8ad373a974a01ea844cc0a.jpeg) **Availability** - **Windows:** Local + Cloud - **macOS:** Cloud only (local support coming later) **How to Use** 1. Select the Recover model 2. Selec the version from the dropdown menu and select “Recover 3” 3. Choose a strength mode (Low/Med/High) - the app defaults the Medium option as the best balanced enhancement. The strength mode controls the intensity of the detail enhanced. ![Screenshot 2026-01-22 at 8.46.01 PM](https://community-cdn.topazlabs.com/original/3X/2/3/23e0f75d15bad7f266f3a5891692f0ca2c293fcf.png) **Recommended usage** - Optimal input size: **1024 × 1024 or smaller** - Larger images are supported, but renders more slowly - Not recommended for highly structured or high-grain images * * * ### Updated File List We’ve updated the **File List** to better reflect generative workflows. You’ll now see: - Which **generative model** was used - Any associated **model settings** - Quick hover access to **Redefine prompts** This makes it much easier to review how an image was processed—especially when mixing Core and Generative models. ![File List UI update](https://community-cdn.topazlabs.com/original/3X/c/f/cf1f3e8ced074ab93ee6c3cb266e9cda8a74d290.jpeg) ![File List UI](https://community-cdn.topazlabs.com/original/3X/0/9/091fd9c83c4a55be9cbebe2366bf8602331afb6e.png) * * * ## Cloud Queue — Small Workflow Improvements In this release, we focused on **workflow refinements** and **stability improvements** for Cloud rendering—not a full overhaul. ### What’s new - **Cloud Queue access directly from the Import page** - **Download All** button for completed Cloud renders - Improved error handling and status updates These changes are meant to reduce friction and make Cloud renders easier to manage, while we continue improving reliability behind the scenes. ![Cloud queue access at import page](https://community-cdn.topazlabs.com/original/3X/7/f/7f1a025f75a846ed4cf22473ab76b7585ea25321.png) **Download all** - Access your downloads with one single button instead of manually downloading each image. The app will take any “Ready for download” status images and download them in the background. ![Download all button](https://community-cdn.topazlabs.com/original/3X/7/4/748b8c28e343399d4f749bd83daa3f3c3380e541.png) * * * **Changelog:** - Added Wonder 2 (Cloud only) - Enabled Recover 3 local rendering on Windows - Added "Download All” added to Cloud Queue - Added Cloud Queue button to Import page - Updated Image AI - File List updated for generative models - Updated error handling for TIFF files in Cloud Compare tool - Fixed HEIC loading issues in some cases - Fixed plugin dialog not appearing - Fixed potential crashes in model downloader - Fixed longest edge preferences not sticking - Fixed Cloud queue naming and refresh issues - Fixed cloud thumbnails in most cases - Fixed cloud filenames being incorrect on upload - Fixed cloud uploads not being deleted in some cases - Fixed cloud errors displaying wrong model name\< - New Features dialog restored with updated slides - Cloud rendering stability improvements - Automatic Lensfun updates - Prevented source file deletion in rare Cloud cases - (v1.1.1) Fixed cloud uploads sometimes deleting files incorrectly - (v1.1.1) Removed neural engine toggle on legacy models on Mac * * * **Known Issues:** - Recover 3 local rendering is not yet available on macOS\*\* - Face Recovery disabled for Wonder 2 - Recover 3 does not support Face Recovery on Cloud - Tooltip not showing for Wonder 2 & Recover 3 when large images over 128 megapixels may fail to process in the cloud - Tooltip not showing for Wonder when an unsupported scale (over 6×) may fail to process in the cloud ---
**Author:** ![jamie-6940](https://community.topazlabs.com/letter_avatar_proxy/v4/letter/j/b5e925/32.png) [@jamie-6940](https://community.topazlabs.com/u/jamie-6940)\ **Post date:** [January 23, 2026, 4:33pm UTC](https://community.topazlabs.com/t/topaz-gigapixel-v1-1-0-v1-1-1/100363/2 "2026-01-23T16:33:32Z")
Wonder2 isn’t working correctly. The scaling / ratio is the weirdest I’ve seen. Seems to chop loads of the image away, example below between them, scaling the image to 10000px on the longest edge, ![image](https://community-cdn.topazlabs.com/original/3X/9/6/96b439ed892e5ecc45343ceecc5975415baf4c93.jpeg) ---
**Author:** ![alanhusband-677420](https://community.topazlabs.com/letter_avatar_proxy/v4/letter/a/7ba0ec/32.png) [@alanhusband-677420](https://community.topazlabs.com/u/alanhusband-677420)\ **Post date:** [January 23, 2026, 4:44pm UTC](https://community.topazlabs.com/t/topaz-gigapixel-v1-1-0-v1-1-1/100363/3 "2026-01-23T16:44:46Z")
You might be experiencing this cloud bug with decimal scale factors: > [@Upscale Issue | Undesired Export Crop](https://community.topazlabs.com/t/upscale-issue-undesired-export-crop/100384): > > I would love to put the new models to the test but for now, everything I feed into the cloud will come out cropped: Did I overlook a setting or run into a bug? ---
**Author:** ![jamie-6940](https://community.topazlabs.com/letter_avatar_proxy/v4/letter/j/b5e925/32.png) [@jamie-6940](https://community.topazlabs.com/u/jamie-6940)\ **Post date:** [January 23, 2026, 5:00pm UTC](https://community.topazlabs.com/t/topaz-gigapixel-v1-1-0-v1-1-1/100363/4 "2026-01-23T17:00:45Z")
no idea to be honest, although cloud-wonder worked perfectly and cloud-wonder-2 chopped it. 🙂 ---
**Author:** ![richardT](https://community.topazlabs.com/letter_avatar_proxy/v4/letter/r/9f8e36/32.png) [@richardT](https://community.topazlabs.com/u/richardT)\ **Post date:** [January 23, 2026, 5:03pm UTC](https://community.topazlabs.com/t/topaz-gigapixel-v1-1-0-v1-1-1/100363/5 "2026-01-23T17:03:42Z")
I get the same thing with wonder and standard max, crops the image after processing ---
**Author:** ![alexandre.topazlabs](https://community.topazlabs.com/letter_avatar_proxy/v4/letter/a/5f9b8f/32.png) [@alexandre.topazlabs](https://community.topazlabs.com/u/alexandre.topazlabs)\ **Post date:** [January 23, 2026, 8:05pm UTC](https://community.topazlabs.com/t/topaz-gigapixel-v1-1-0-v1-1-1/100363/6 "2026-01-23T20:05:38Z")
@richardT @jamie-6940 I added you to the bug thread. I can confirm that this is the issue you have ---
**Author:** ![AceNoGlow](https://community.topazlabs.com/letter_avatar_proxy/v4/letter/a/f4b2a3/32.png) [@AceNoGlow](https://community.topazlabs.com/u/AceNoGlow)\ **Post date:** [January 23, 2026, 9:42pm UTC](https://community.topazlabs.com/t/topaz-gigapixel-v1-1-0-v1-1-1/100363/7 "2026-01-23T21:42:21Z")
A photo enhancement model that is cloud only is an interesting choice. Is it really that resource intensive or is this just a way to get people to consume cloud credits? Are there plans to make this able to run locally? ---
**Author:** ![alexandre.topazlabs](https://community.topazlabs.com/letter_avatar_proxy/v4/letter/a/5f9b8f/32.png) [@alexandre.topazlabs](https://community.topazlabs.com/u/alexandre.topazlabs)\ **Post date:** [January 23, 2026, 9:51pm UTC](https://community.topazlabs.com/t/topaz-gigapixel-v1-1-0-v1-1-1/100363/8 "2026-01-23T21:51:23Z")
> [@AceNoGlow](#): > > is this just a way to get people to consume cloud credits? There are no cloud credits in Topaz Gigapixel, it’s free. The model was not ready to work locally, it will come later. ---
**Author:** ![mikmod1](https://community.topazlabs.com/user_avatar/community.topazlabs.com/mikmod1/32/239469_2.png) [@mikmod1](https://community.topazlabs.com/u/mikmod1)\ **Post date:** [January 23, 2026, 9:53pm UTC](https://community.topazlabs.com/t/topaz-gigapixel-v1-1-0-v1-1-1/100363/9 "2026-01-23T21:53:42Z")
I’m noticing very ‘artsy’ approach of the Recover v3 model on all three ‘strengths’, is it intended? 🙂 It’s in T-Gigapixel AND also in T-Photo, in GPU mode. ![obraz](https://community-cdn.topazlabs.com/original/3X/7/3/730fea0375f2557150c1f9b77c4276fc40026474.jpeg) ..whereas, Recover v2: ![obraz](https://community-cdn.topazlabs.com/original/3X/9/7/975ff58193a8dcc213fa010fcae581a94e304fd9.jpeg) …and v1: ![obraz](https://community-cdn.topazlabs.com/original/3X/5/2/52b35dc45a3f9834b3b7130b30c264dce1dc0e40.jpeg) ---
**Author:** ![alexandre.topazlabs](https://community.topazlabs.com/letter_avatar_proxy/v4/letter/a/5f9b8f/32.png) [@alexandre.topazlabs](https://community.topazlabs.com/u/alexandre.topazlabs)\ **Post date:** [January 23, 2026, 9:58pm UTC](https://community.topazlabs.com/t/topaz-gigapixel-v1-1-0-v1-1-1/100363/10 "2026-01-23T21:58:42Z")
Those are good results for Recover. If you want more details on this image you will need to use Redefine. This is going to generate details that are not there in the image. Keep in mind that this image is 192x192 pixels, lower than the resolution of the first Nintendo. For the difference between the models, Recover v3 is more about fidelity and less about adding details that aren’t there. The other models will always be there so you have the choice 🙂 ---
**Author:** ![mikmod1](https://community.topazlabs.com/user_avatar/community.topazlabs.com/mikmod1/32/239469_2.png) [@mikmod1](https://community.topazlabs.com/u/mikmod1)\ **Post date:** [January 23, 2026, 10:01pm UTC](https://community.topazlabs.com/t/topaz-gigapixel-v1-1-0-v1-1-1/100363/11 "2026-01-23T22:01:04Z")
Yup, that’s why I used this thumbnail for testing almost since the birth of Gigapixel. 🙂 Recover v3 is also very smeary on low resolution (600x800) camera-taken grayscale text page from MMS message, so I had to use Wonder v2 for it to look great. Roget that - Recover v3 isn’t for the lowres animated stuff. 🫡 🙂 And uploading this thumbnail to Wonder v2 cloud yielded an error during processing. Now it’s the time to take on old Windows XP wallpapers! ---
**Author:** ![alexandre.topazlabs](https://community.topazlabs.com/letter_avatar_proxy/v4/letter/a/5f9b8f/32.png) [@alexandre.topazlabs](https://community.topazlabs.com/u/alexandre.topazlabs)\ **Post date:** [January 23, 2026, 10:07pm UTC](https://community.topazlabs.com/t/topaz-gigapixel-v1-1-0-v1-1-1/100363/12 "2026-01-23T22:07:36Z")
> [@mikmod1](#): > > Roget that - Recover v3 isn’t for the lowres animated stuff. it’s worth a try! But the new models were requested for more realistic images like low-res photos or heavily cropped animals in a photo, etc. Otherwise there was too many artifacts. The more we see users testing the models, the more we can add an accurate description of what they are meant for in our release, this is actually good to see this test. ---
**Author:** ![mikmod1](https://community.topazlabs.com/user_avatar/community.topazlabs.com/mikmod1/32/239469_2.png) [@mikmod1](https://community.topazlabs.com/u/mikmod1)\ **Post date:** [January 23, 2026, 10:11pm UTC](https://community.topazlabs.com/t/topaz-gigapixel-v1-1-0-v1-1-1/100363/13 "2026-01-23T22:11:08Z")
Trying to upscale a meme, photo-like image this time, with Recover v3: ![obraz](https://community-cdn.topazlabs.com/original/3X/2/e/2eb294fe424cbab76975f227c0e2883f98fe141c.jpeg) ![obraz](https://community-cdn.topazlabs.com/original/3X/8/5/8577c9a03f7f08f9c419549254d06c43f63341a4.jpeg) ![obraz](https://community-cdn.topazlabs.com/original/3X/0/c/0c7761fd831b97de6f3f7da5d91318e72653c824.jpeg) ---
**Author:** ![alexandre.topazlabs](https://community.topazlabs.com/letter_avatar_proxy/v4/letter/a/5f9b8f/32.png) [@alexandre.topazlabs](https://community.topazlabs.com/u/alexandre.topazlabs)\ **Post date:** [January 23, 2026, 10:12pm UTC](https://community.topazlabs.com/t/topaz-gigapixel-v1-1-0-v1-1-1/100363/14 "2026-01-23T22:12:48Z")
Can you send us that image? I would like to test and share with the development team. ---
**Author:** ![mikmod1](https://community.topazlabs.com/user_avatar/community.topazlabs.com/mikmod1/32/239469_2.png) [@mikmod1](https://community.topazlabs.com/u/mikmod1)\ **Post date:** [January 23, 2026, 10:14pm UTC](https://community.topazlabs.com/t/topaz-gigapixel-v1-1-0-v1-1-1/100363/15 "2026-01-23T22:14:13Z")
Of course! ![synek bo jak ja cię](https://community-cdn.topazlabs.com/original/3X/3/7/372e6bc4d374786a2612b3cf9d45aae3c8a3b90f.jpeg) ![52906](https://community-cdn.topazlabs.com/original/3X/1/7/17f6069f8e7c2657f840d6b2b03c2d0b891eb323.png) ---
**Author:** ![Ange.topazlabs](https://community.topazlabs.com/user_avatar/community.topazlabs.com/ange.topazlabs/32/175061_2.png) [@Ange.topazlabs](https://community.topazlabs.com/u/Ange.topazlabs)\ **Post date:** [January 23, 2026, 10:27pm UTC](https://community.topazlabs.com/t/topaz-gigapixel-v1-1-0-v1-1-1/100363/16 "2026-01-23T22:27:28Z")
A post was merged into an existing topic: [Upscale Issue | Undesired Export Crop](https://community.topazlabs.com/t/upscale-issue-undesired-export-crop/100384/10) ---
**Author:** ![mikmod1](https://community.topazlabs.com/user_avatar/community.topazlabs.com/mikmod1/32/239469_2.png) [@mikmod1](https://community.topazlabs.com/u/mikmod1)\ **Post date:** [January 23, 2026, 10:27pm UTC](https://community.topazlabs.com/t/topaz-gigapixel-v1-1-0-v1-1-1/100363/17 "2026-01-23T22:27:47Z")
Another attempt on Recovery v3 (a raunchy tweet of a fundamentalist). 🙂 Clearly, there’s some issue with this cell-like texture. ![obraz](https://community-cdn.topazlabs.com/original/3X/c/7/c7d1c4a2dd07c9dbffd543178928a5ee7318a001.jpeg) ---
**Author:** ![TPX](https://community.topazlabs.com/user_avatar/community.topazlabs.com/tpx/32/194727_2.png) [@TPX](https://community.topazlabs.com/u/TPX)\ **Post date:** [January 23, 2026, 10:57pm UTC](https://community.topazlabs.com/t/topaz-gigapixel-v1-1-0-v1-1-1/100363/18 "2026-01-23T22:57:04Z")
> [@TPX](#): > > I am currently testing reducing the image to the pixel density of a medium format camera with 100 MP in order to achieve the pixel size of the medium format camera, in the hope that the models will be able to handle it better. I’ll have to check again—if that’s really true. ![Screenshot 2026-01-23 235225](https://community-cdn.topazlabs.com/original/3X/f/f/ffeb2e60cab7faae4336ab8c14a511ac3ff3b806.jpeg) Wonder 2 - Pixel Dense image as input - 3x upscale * * * ![Screenshot 2026-01-23 235235](https://community-cdn.topazlabs.com/original/3X/1/b/1bb2c7b679cd1ff9049d837af02cf98e0c1a224c.jpeg) Wonder 2 Native res as input - 2x upscale * * * ![Screenshot 2026-01-23 235313](https://community-cdn.topazlabs.com/original/3X/3/5/35fc6f3a0e0b70dbbf6327773d221672dfa2b8ed.jpeg) Hifi V2 - Pixel Dense image as input - 3x upscale * * * ![Screenshot 2026-01-23 235321](https://community-cdn.topazlabs.com/original/3X/d/7/d79a29c61984f60f809c25d09fb6fd4089be5411.jpeg) Standard MAX - Pixel Dense image as input - 3x upscale ---
**Author:** ![alexandre.topazlabs](https://community.topazlabs.com/letter_avatar_proxy/v4/letter/a/5f9b8f/32.png) [@alexandre.topazlabs](https://community.topazlabs.com/u/alexandre.topazlabs)\ **Post date:** [January 23, 2026, 11:32pm UTC](https://community.topazlabs.com/t/topaz-gigapixel-v1-1-0-v1-1-1/100363/19 "2026-01-23T23:32:24Z")
@mikmod1 Here are the results of my tests: Wonder V2 gave me the best results: ![image](https://community-cdn.topazlabs.com/original/3X/6/1/612cb7c3d7a0e1a0e1c3aac9ac25091f7271a1c8.jpeg) Then Recover V2: ![image](https://community-cdn.topazlabs.com/original/3X/5/5/554fdfc97812a7676cbad23bb8e88bc5b019f609.jpeg) **Recover v3 didn’t work on this image. I shared with the development team.** ---
**Author:** ![mikmod1](https://community.topazlabs.com/user_avatar/community.topazlabs.com/mikmod1/32/239469_2.png) [@mikmod1](https://community.topazlabs.com/u/mikmod1)\ **Post date:** [January 24, 2026, 12:24am UTC](https://community.topazlabs.com/t/topaz-gigapixel-v1-1-0-v1-1-1/100363/20 "2026-01-24T00:24:02Z")
Thank you! Same result on my RTX 3090 with Recover v2, so we know now, there’s something wrong with Recover v3 output, possibly… 🙂 Wonder v2 works wonders indeed with this image - I had to see to believe it myself. There’s a bug though - if the amount of upscaling exceeds 6x, the cloud processing errors out. [Next page](https://community.topazlabs.com/t/topaz-gigapixel-v1-1-0-v1-1-1/100363.md?page=2)