gen‑ai.news
← Back
Multimodal

DaVinci Resolve 21 Officially Released With New Photo Editing, AI Tools, and Much More

DaVinci Resolve 21 Officially Released With New Photo Editing, AI Tools, and Much More

Blackmagic Design has officially released DaVinci Resolve 21, completing a development cycle that the company describes as one of the largest in the application's history. The update spans virtually every major section of the software, with additions ranging from a purpose-built photo editing environment to AI-assisted tools designed to reduce manual labor on common post-production tasks.

The most structurally significant addition is a new Photo page, which brings still-image editing into Resolve as a first-class workflow rather than a workaround through the existing Cut or Color pages. This positions the software more directly against dedicated photo editors, and it reflects a broader trend of Blackmagic expanding Resolve beyond its origins as a color grading tool into a more general creative suite.

On the AI side, the release adds a range of tools that touch color grading, editing, and visual effects. While Blackmagic has not historically been the fastest company to integrate generative features, Resolve 21 appears to incorporate several practical AI-driven capabilities aimed at speeding up repetitive tasks rather than generating content from scratch. The specifics span areas like object-based workflows and automated analysis, continuing the direction set by earlier AI features such as Magic Mask and Speed Warp.

The update also extends codec and camera format support, which matters to cinematographers and editors who work with newer acquisition formats and need reliable decode performance inside a single application. Workflow improvements across the Fairlight audio page and Fusion visual effects environment round out the release. DaVinci Resolve 21 is available as a free download, with the full Studio version carrying its existing one-time license fee - a pricing model that continues to differentiate Blackmagic from subscription-based competitors.

Read at PetaPixel →
Share:X

Enjoy this story? Get the next one in your inbox.

Twice a week: the most important stories in generative image and video AI, distilled into a 2-minute read.

Free. Unsubscribe any time. No spam, ever.

Your next read

No image
Multimodal

Fine-tune video and image models at scale with NVIDIA NeMo Automodel and 🤗 Diffusers

NVIDIA and Hugging Face have joined forces to bring large-scale fine-tuning of image and video diffusion models into the NeMo Automodel framework, integrated with the Diffusers library. The collaboration aims to make distributed training more accessible for teams working with models that would otherwise be difficult to fine-tune on limited hardware. The result is a more streamlined path from a pretrained diffusion model to a customized one, without requiring deep infrastructure expertise.

No image
Multimodal

Thinking Machines Lab Releases Inkling: A 975B-Parameter Open-Weights Multimodal MoE With 41B Active Parameters And Controllable Thinking Effort

Thinking Machines Lab has released Inkling, a 975B-parameter open-weights multimodal model built on a Mixture-of-Experts architecture that keeps only 41B parameters active at any given time. Licensed under Apache 2.0, it accepts text, image, and audio inputs and offers a 1M-token context window. Rather than competing for top benchmark rankings, the model is positioned as a customizable base with adjustable reasoning depth.