Models & Labs
OpenAI Releases GPT-Image 2.6 with GIF Capabilities
Matt Wolfehigh confidence
Why it matters
- →Expands image models into short-form animation, a high-demand use case.
- →Native GIF editing reduces reliance on post-processing software.
- →Signals continued rapid iteration in OpenAI's multimodal capabilities.
OpenAI has updated its flagship image model to version 2.6, adding significant new capabilities for animated content. The update introduces native generation of animated GIFs and tools for editing existing animations, expanding the model's utility beyond static imagery. Early speed tests indicate performance improvements, though specific benchmark metrics were not detailed in initial reports. This release positions OpenAI to compete more directly with specialized video and animation AI tools.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1OpenAI Unveils GPT-5.6 and ChatGPT Work App
The AI Advantage · July 10, 2026 · Related
- 2OpenAI Releases GPT-5.6 with Enhanced Capabilities
Matt Wolfe · July 11, 2026 · Same story
- 3OpenAI Launches ChatGPT Images 2.5
OpenAI · September 8, 2026 · Related
- 4OpenAI Launches ChatGPT Sketch for Image Creation
The Verge AI · September 8, 2026 · Related
- 5OpenAI Releases ChatGPT Images 2.5 and Work Browser
Lev Selector · September 11, 2026 · Related
- 6OpenAI Introduces GPT-6 with Upgraded Computer Use
Matt Wolfe · September 24, 2026 · Same story
- 7OpenAI launches GPT-6 with interactive 'Intelligent UI'
WIRED AI · October 7, 2026 · Related
- 8OpenAI launches GPT-6 with interactive Intelligent UI
TechCrunch AI · October 7, 2026 · Related
What happened next
- 9GPT-6 Astra Edits Qwen Weights Directly
Lev Selector · November 6, 2026 · Background
Follow this story
Open the full story →ChatGPT adds native GIF generation with Images 2.6
4 developments
- Nov 4 · The Verge AI
ChatGPT adds native GIF generation with Images 2.6 - Nov 6 · Matt Wolfe
OpenAI Releases GPT-Image 2.6 with GIF Capabilities (This article) - Nov 6 · The AI Advantage
ChatGPT Images 2.6 Adds GIFs and Dot Upgrades - Nov 6 · Lev Selector
OpenAI Images 2.6 Released↳ The update brings improvements in quality and consistency.
More from Matt Wolfe
© Matt WolfeModels & Labsvideo
Google Launches Gemini Omni 1.2 Flash and Free Video Gen
Google released Gemini Omni 1.2 Flash and integrated free AI video generation into Google Vids for users.
Matt Wolfe
© Matt WolfeOpen Sourceimage
Pruna Releases PH3 Image Open-Weight Model
Pruna has released PH3 Image, an open-weight image generation model available on Hugging Face with specific hardware requirements.
Matt Wolfe
© Matt WolfeOpen Sourcevideo
Pika Releases H3 Flex Open-Weight Video Model
Video AI startup Pika has released its H3 Flex model as open-weight, allowing developers to run it on their own infrastructure.
Matt Wolfe
More in Models & Labs
Models & Labsother
llama.cpp b12177 adds CUDA 13 and ROCm 10
This release quietly closes the hardware gap for local inference by adding default support for CUDA 13.5 and ROCm 10.0 alongside existing CUDA 12 builds. AMD GPU users finally get first-class parity with NVIDIA, while Snapdragon mobile chips gain dedicated NPU acceleration paths. Apple Silicon KleidiAI is explicitly disabled here, a notable regression for Mac performance that suggests ongoing tuning issues. The inclusion of OpenVINO and SYCL backends further cements llama.cpp as the universal runtime for inference across nearly every major silicon architecture.
llama.cpp Releases
Models & Labsmodels
llama.cpp adds Kimi K3.1-Pro support
Kimi’s new K3.1-Pro model joins the llama.cpp ecosystem, bringing a distinct architectural twist to local inference. By replacing full-attention MLA layers with DSA (Dynamic Sparse Attention) and linear-attention KDA layers, this release tests how well sparse caching handles hybrid attention patterns. The implementation keeps indexer precision high to avoid quality loss during top-k selection, ensuring the model runs accurately on consumer hardware. This expands the library’s reach into newer Chinese open-weight models that rely on complex memory management.
llama.cpp Releases
Models & Labsother
llama.cpp b12182 release with CUDA 13 and ROCm 10
This release quietly cements llama.cpp as the universal inference runtime by adding default builds for CUDA 13.5 and ROCm 10.0 across Linux and Windows. The inclusion of ROCm 10 means AMD GPU users no longer need custom compilation to access modern acceleration, effectively closing the gap with NVIDIA's ecosystem support. While KleidiAI on Apple Silicon is disabled in this build, the broader platform coverage ensures that local inference remains accessible on virtually any hardware configuration without manual setup.
llama.cpp Releases