Images and video
Models and products that make, edit or understand images and video. The Atlas has logged 234 launches and papers on it since 6 February 2023, 98 of them in 2026.
Google DeepMind, Alibaba Qwen (Tongyi) and OpenAI have the most.
Key launches
The 60 most significant of 234, newest first. Every launch in the Atlas
- Kling Image 4.0 Kling AI · 18 November 2026
Kling AI launched Kling Image 4.0, an image model with native 8K output, up to 2,000 characters of text per image and coordinated sets of up to 10 images. - Six new MAI models (including MAI Code 2) Microsoft · 17 November 2026
Microsoft unveiled six AI models at Ignite covering coding, cybersecurity, images and voice, and said it will license the models' weights for customers to customize. - MAI Code 2, MAI Code 2 Flash, MAI Cyber 2 Flash, MAI Image 2.7, MAI Realtime 1, Dragon Copilot Transcribe and Decision 1.1 Microsoft AI · 17 November 2026
Microsoft AI released seven new MAI models at Ignite 2026, covering coding, cyber defense, image, realtime voice, medical transcription and routing, priced well below rival models. - Kling Image 4.0 Kuaishou · 17 November 2026
Kuaishou launched Kling Image 4.0 with native 8K image generation and up to 10 coordinated images from one prompt, also available through an API. - Suno Visuals Suno · 17 November 2026
Suno launched Visuals, which turns songs into lip-synced AI video clips of up to 15 seconds and generates images, using H3 Move, a model based on MiniMax's H3. - Visuals Suno · 17 November 2026
Suno launched Visuals, a feature that lets users generate 15-second video clips for their songs and join them into a full music video, built on a MiniMax model. - OpenAI CSAM Image Classifier (omni-moderation-csam-latest) OpenAI · 16 November 2026
OpenAI released an image classifier that detects potential CSAM, including AI-generated material, free to vetted organizations through the API, with new ChatGPT warnings and… - Foundation Models framework Apple · 12 November 2026
Apple updated its Foundation Models framework to support server LLMs like Claude and Gemini alongside on-device models, adding Dynamic Profiles, image understanding, and Private… - Seedance 2.5 Flash ByteDance · 12 November 2026
ByteDance's Volcano Engine released Seedance 2.5 Flash, a lighter video model that it says is twice as fast as Seedance 2.5 and about 34% cheaper at 720p. - Gemini Decision 1 Google · 11 November 2026
Google released Gemini Decision 1 and the Gemini Decisions API, which scores up to 1,000 closed-set questions per request in one forward pass at $0.10 per 1M input tokens. - Adobe Max 2026 Sneaks (experimental AI features) Adobe · 11 November 2026
Adobe showed experimental AI projects at Max, including a tool that turns images into explorable 3D scenes and Project Screen Test, which designs AI characters through… - MiniMax-H3-Image MiniMax · 10 November 2026
MiniMax launched H3-Image, an open-weights image model that makes 16-megapixel 4K images in 10 to 20 seconds and accepts up to 16 reference images. - Firefly AI Assistant upgrades and Creative Cloud local MCP Adobe · 10 November 2026
At MAX, Adobe previewed a local MCP so third-party agents can edit Creative Cloud projects, and added Plan Mode, a Model Selector and always-on agents to Firefly AI Assistant. - Muse Ember Meta · 9 November 2026
Meta released Muse Ember, its smallest and cheapest Muse model for high-volume agent work, at $0.10 per million input tokens and $0.50 per million output tokens with a 1M-token… - Adobe Firefly Foundry models for Disney Adobe · 9 November 2026
Adobe and Disney signed a multiyear deal at Adobe MAX to build proprietary, artist-led generative AI models on Adobe Firefly Foundry for Disney's production pipeline. - WorkRally Rally-Video Tencent · 6 November 2026
Tencent upgraded its WorkRally creation platform with three video models, Rally-Video, Rally-Video-edit-2.0 and UpScale-rally, and says the upscaler cuts processing time by 80%. - WeLM-Image WeChat (Tencent) · 5 November 2026
WeChat's team published WeLM-Image, a unified image model with 31.7B stored parameters and about 5.4B activated per target latent token, built for single-GPU deployment. - Gemini Omni 1.2 Flash Google DeepMind · 5 November 2026
Google released Gemini Omni 1.2 Flash, a video generation and editing model with native 15-second clips and pricing 30% lower than Omni 1.1. - Genie 4 Google DeepMind · 27 October 2026
Google DeepMind announced Genie 4, a world model that generates interactive simulations with native audio, music and dialogue, now in research preview for trusted testers. - Wan3.0 (video) Alibaba (Qwen) · 24 August 2026
Hosted Wan3.0 makes native 30-second clips up to 1080p with audio and accepts documents, slides, spreadsheets and webpages as references. - Seedance 2.5 ByteDance · 31 July 2026
Seedance 2.5 makes 30-second single-pass clips with synced audio, up to 50 multimodal references, region-level edits and 4K, previewed 2026-06-23. - MiniMax H3 (Hailuo) MiniMax · 31 July 2026
MiniMax H3 is an open-weights audio-video model that makes 2K, 15-second clips with native stereo sound, priced below a third of mainstream models at 2K. - FLUX 3 (early access) Black Forest Labs · 23 July 2026
FLUX 3: one multimodal flow model for image, video with native audio, and robot-action prediction; open FLUX 3 Dev promised. - Gemini Omni (Omni Flash) Google DeepMind · 19 May 2026
Gemini Omni Flash makes video from mixed image, audio, video and text input and edits it conversationally; first of a planned family. - Gemini Omni Flash Google DeepMind · 19 May 2026
Gemini Omni Flash takes text, images, audio and video in one prompt and outputs editable video, folding the Veo line into Gemini itself. - gpt-image-2 (ChatGPT Images 2.0) OpenAI · 21 April 2026
gpt-image-2 / ChatGPT Images 2.0: an image model with built-in thinking (web search, multi-image output, self-checks), up to 2K. - Seedance 2.0 studio cease-and-desists ByteDance · 16 February 2026
Disney, Netflix, Paramount, Warner Bros. and Sony sent cease-and-desist letters over Seedance 2.0; the MPA called it 'systemic infringement'. - Seedance 2.0 ByteDance · 12 February 2026
Seedance 2.0 jointly generates audio and video from text, image, audio and video references (9+3+3 per prompt), and Hollywood objected to it. - Kling 3.0 Kuaishou · February 2026
Kling 3.0 unifies video, image, audio and editing, with multi-shot storytelling, native audio, multilingual dialogue and up to 15 seconds per generation. - FLUX.2 [pro / flex / dev / klein] Black Forest Labs · 25 November 2025
FLUX.2 pairs a Mistral-3 24B vision-language model with a rectified-flow transformer, and supports up to 10 reference images and 4MP editing, with a 32B open [dev] model. - Nano Banana Pro (Gemini 3 Pro Image) Google DeepMind · 20 November 2025
Nano Banana Pro, built on Gemini 3 Pro, renders legible multilingual text, outputs up to 4K, blends up to 14 images and keeps 5 people consistent. - SAM 3 and SAM 3D Meta · 19 November 2025
SAM 3 segments and tracks every instance matching a text or exemplar concept; SAM 3D reconstructs objects and human bodies from one image. - ERNIE 5.0 Baidu · 13 November 2025
Natively autoregressive omni-modal model trained from scratch on text, image, video and audio with a 2.4T-parameter ultra-sparse MoE (about 3% active). - Marble World Labs · 12 November 2025
Marble, World Labs' first public product, generates persistent 3D worlds from text, images, video or coarse layouts and exports Gaussian splats, meshes or video. - Getty Images v Stability AI (UK High Court judgment) Getty Images / Stability AI · 4 November 2025
UK High Court rejected Getty's secondary copyright claim, holding that Stable Diffusion's weights are not an 'infringing copy', and made only narrow trade-mark findings for… - Sora 2 and the Sora app OpenAI · 30 September 2025
Sora 2 generates video with synchronized dialogue and sound, better physics, and "cameos" of real people, launched with a social Sora app. - Nano Banana (Gemini 2.5 Flash Image) Google DeepMind · 26 August 2025
Gemini 2.5 Flash Image ("nano-banana") blends several images, keeps characters consistent and edits by natural-language instruction; $0.039 per image via API. - Genie 3 Google DeepMind · 5 August 2025
Genie 3 turns a text prompt into a navigable world rendered in real time at 24 fps and 720p, holding consistency for a few minutes. - Qwen-Image (20B MMDiT) Alibaba (Qwen) · 4 August 2025
20B MMDiT image model with native text rendering for English and Chinese, opened under Apache 2.0 with a technical report. - V-JEPA 2 Meta · 11 June 2025
1.2B-param video world model pretrained on 1M+ hours of video, then adapted on only 62 hours of robot data for zero-shot pick-and-place planning. - Studios v. Midjourney (copyright suit) Disney, Universal, Warner Bros. Discovery / Midjourney · 11 June 2025
Disney and Universal sued Midjourney over Darth Vader, Minions, Simpsons-style outputs; Warner Bros. Discovery filed its own suit in September 2025. - Seedance 1.0 ByteDance · 10 June 2025
Seedance 1.0 generates 1080p multi-shot video from text or image with strong motion; a top-ranked model on Artificial Analysis at launch. - FLUX.1 Kontext Black Forest Labs · 29 May 2025
FLUX.1 Kontext is one flow-matching model for in-context image generation and editing from text plus image input, and BFL claims it is up to 8x faster than rivals. - Veo 3 Google DeepMind · 20 May 2025
Veo 3 generates video with synchronized dialogue, sound effects and ambient audio; Google calls it the first video model with native audio. - Gen-4 Runway · 31 March 2025
Gen-4 keeps characters, objects and locations consistent across shots from a single reference image, with no fine-tuning. - GPT-4o image generation OpenAI · 25 March 2025
ChatGPT gets native GPT-4o image generation, replacing DALL-E 3: multi-turn editing and inpainting, Pro users first. - Wan2.1 (T2V 1.3B and 14B, I2V 14B) Alibaba (Qwen) · 25 February 2025
Alibaba open-sources a full video-generation suite under Apache 2.0; the 1.3B text-to-video model needs 8.19 GB VRAM, the 14B tops open rivals on company benchmarks. - Cosmos World Foundation Model Platform NVIDIA · 7 January 2025
NVIDIA's Cosmos is an open platform of pretrained world foundation models, video curation pipeline and tokenizers for training physical-AI systems. - Veo 2 Google DeepMind · 16 December 2024
Veo 2 text-to-video with up to 4K resolution and cinematography control, released with an Imagen 3 update and the Whisk remix tool. - Genie 2 Google DeepMind · 4 December 2024
Foundation world model that turns one image into a playable 3D environment, consistent for up to a minute. - HunyuanVideo Tencent · 3 December 2024
HunyuanVideo, a 13B-parameter open-source video model, matched closed models like Runway Gen-3 and Luma 1.6 in Tencent's 1,533-prompt human eval. - FLUX.1 [pro / dev / schnell] Black Forest Labs · 1 August 2024
Black Forest Labs launches with FLUX.1: three 12B image models (pro API, dev open-weight non-commercial, schnell Apache 2.0) and a $31M seed. - Segment Anything Model 2 (SAM 2) Meta · 29 July 2024
Real-time promptable segmentation for images and video, ~44 fps, with SA-V dataset of 51K videos and 600K+ masklets; Apache 2.0. - Gen-3 Alpha Runway · 17 June 2024
Gen-3 Alpha, trained on new large-scale multimodal infrastructure, markedly improves fidelity, motion and temporal control and human faces. - Kling (1.0) Kuaishou · June 2024
Kuaishou's Kling opened as a beta in China, a Sora-like text/image-to-video model that was publicly usable months before Sora. - GPT-4o OpenAI · 13 May 2024
One network handles text, audio and images end to end; GPT-4o costs half of GPT-4 Turbo and reaches free ChatGPT users. - Stable Diffusion 3 (early preview) Stability AI · 22 February 2024
Stable Diffusion 3 was previewed as a diffusion transformer trained with flow matching, at 800M to 8B parameters and waitlist-only. - Sora (technical preview) OpenAI · 15 February 2024
OpenAI previewed Sora, a diffusion transformer that generates up to one-minute HD video from text and was shown only to red teamers and select creatives. - Stable Diffusion XL 1.0 Stability AI · 26 July 2023
SDXL 1.0 ships with open weights, a 3.5B-parameter base plus refiner and native 1024x1024 output, and runs on 8GB consumer GPUs. - ControlNet Stanford University · 10 February 2023
ControlNet adds spatial control (edges, depth, pose, segmentation) to pretrained text-to-image diffusion models without retraining the base model.
Most active labs
- Google DeepMind 37 launches and papers
- Alibaba Qwen (Tongyi) 26 launches and papers
- OpenAI 18 launches and papers
- ByteDance Seed 13 launches and papers
- Runway 11 launches and papers
- Kuaishou 8 launches and papers
- Stability AI 8 launches and papers
- Black Forest Labs 7 launches and papers