Hello everyone!
We’re excited to share an early look at Denoise Max, our most powerful denoising model to date. Starting today, Denoise Max is available in beta on the cloud for one week until April 23rd, free for all users with a Topaz Labs account. No credits needed.
To gain access to the open beta, please fill out this form with your email and we will grant you access.
Once we have granted you access and notified you by email, access the model from this link after logging in to your Topaz Labs account.
Express Beta with Denoise Max
You can find the Denoise Max model from the “+ More” dropdown.
After trying this model, please fill out the following survey for feedback on the model.
Survey here
Denoise Max — Generative Denoising for Extreme Noise
Our existing denoise models handle low and medium noise well. But at the high end of the noise spectrum, results can get patchy, and even a technically clean image can come out looking soft. That softness isn’t a processing artifact. It’s missing information. Heavy noise doesn’t just sit on top of an image, it buries the detail that was there in the original scene. Once that detail is obscured, a standard denoise pass has nothing to recover it from.
Denoise Max approaches this differently. Built on the same generative foundation as Wonder 2, it uses the full context of the image to reconstruct detail that noise has hidden rather than simply filtering noise away. The result is a clean image with sharpness and texture restored, not just a smoother version of a damaged one.
Denoise Max runs on the same underlying model as Wonder 2, so processing speed is similar. In practice it tends to feel faster, since it’s processing at your image’s native resolution rather than upscaling to a larger output.
If your images have high ISO noise, were shot in low light, or just haven’t responded well to standard denoise models, Denoise Max is the place to start.
Try it and share your feedback
Denoise Max is available on the cloud today through April 23rd.
We want to hear how it performs on your images, especially on shots that have given standard denoise models trouble in the past. Drop your results and feedback in this thread.
