Runway

Runway, Pika, Magnific, and Promptsref added Seedream 5.0 Pro access. Magnific advertised unlimited 1.5K generations for a month, while Runway highlighted reference images and text in up to 14 languages.

Google launched Gemini Omni Flash for video generation and editing in the Gemini API and AI Studio at $0.10 per second. Runway, Magnific and Higgsfield rolled it out on day one, so creators can test VFX, real-footage edits and voice-directed scene changes.

Runway introduced Agent 2.0 to turn a prompt into marketing briefs, creative assets, and performance analysis across platforms and markets. Try it if you want campaign planning and iteration inside one workflow instead of separate tools.

Runway released ad localization that turns a single image into market-specific variants across languages. Use it to keep multilingual ad production inside one creative tool instead of rebuilding assets for each region.

Runway opened a ChatGPT integration so users can generate and edit Runway video and image outputs without leaving a chat thread. Creator tests around Aleph 2.0 also found stronger reference-based control, even when Seedance looked more natural in side-by-side results.

Creators are using Seedance 2 prompts that specify left-to-right staging, foreground order, and no-line negatives to reduce first-frame failures and artifacts. The pattern is being reused for crowd scenes, chase shots, ad concepts, and emotion tests across Runway and Dreamina handoffs.

Runway expanded its Lionsgate relationship into a joint original-IP development program and opened a sold-out New York AI Film Festival premiere the same day. Follow the studio co-development, screenings, and creator sessions if you work in film.

PJ Accetturo unveiled a 5-minute teaser for the hybrid feature film Nexus, made by three people in two weeks with Dreamina AI, Octo, and Seedance 2.0. The result shows Seedance-style workflows reaching music videos, ad concepts, and longer camera-path sequences.

Runway said token consumption rose 50% in six weeks, power users 140%, and enterprise NDR hit 300%. Those figures, plus $3K ad-remake claims and a nearly 100-startup Builders cohort, put concrete adoption numbers behind AI video.

Creators used Seedance 2.0 for 15-second single takes, FPV camera paths, anime action, and ad-style sequences across Mitte, Runway, InVideo, and SocialSight. Use storyboard or character art plus structured prompts for camera beats, dialogue, and motion instead of short text-only prompts.

Runway opened Edit Studio, putting Aleph 2.0’s localized video edits in the main app so users can change only selected parts of a shot. Watch for render-to-video refinements and agency workflow savings as the tool rolls out.

Figma shipped plan mode, a messaging queue, web search and fetch, and pinned comments for Make. The update adds more guided checkpoints to prompt-driven prototype generation as Figma keeps pushing AI workflows beyond plain chat.

Runway put Aleph 2.0 on its API for up to 30 seconds of 1080p editing across multi-shot sequences while changing only selected elements. A same-day creator test inside Adobe Firefly suggests early demand, so watch for broader end-to-end editing workflows.

Creator tests showed Firefly AI Assistant building merch lines from one reference image, handing text-heavy work to Nano Banana Pro, and batching retouching across Photoshop and Lightroom. That broadens the public-beta story beyond auto-crops, though most of today’s proof came from sponsored creator demos rather than a new Adobe announcement.

Runway joined NVIDIA's new Cosmos Coalition as a founding member, and Runway says the group's first project is a base model it is codeveloping with NVIDIA. NVIDIA also says Cosmos 3 is fully open with weights and post-training recipes, so teams can track the shared world-model stack.

Runway said its API now includes Seedance 2.0, GPT Image 2, HappyHorse 1.0, Nano Banana Pro, and Magnific Precision Upscaler V2. Try the new cross-model pipeline if you need image-to-video, upscaling, or mixed asset production inside Runway.

Runway published Last Night as the next Project Luxo short, initially describing it as a fully AI-generated film made in a single day by one creator. The release drew crediting questions, and Runway later clarified the work was made internally by umpherj, so readers should note the updated attribution.

Runway opened ticket sales for its AI Film Festival in New York, led by a pre-show conversation with Ron Howard and a slate of 10 finalist films. It matters because the event packages AI film alongside advertising, design, new media, gaming, and fashion rather than a single-tool showcase.

Runway launched an MCP connector that lets Claude, ChatGPT, Cursor, Replit, and other clients generate images and video with models including Gen-4.5 and Seedance 2.0. It matters because it moves Runway’s model catalog into the agent clients where creators already plan and script work.

Runway launched Project Luxo and centered it on The Rogue, a fully AI-generated 10-minute film made in under a month by one creator. The project gives filmmakers a longer-form benchmark than single-scene demos, though Runway's uncanny-valley threshold claim is company framing.

Creator posts showed Seedance 2.0 running inside Runway, Hailuo, InVideo, and Leonardo, with examples ranging from cinematic action clips to a four-minute short. That matters because Seedance is behaving more like a portable video engine inside broader creator stacks, not just a single-destination model.

Creator tests show Aleph 2.0 can relight, restyle, and swap environments while preserving motion across multishot clips. Reviewers also report weaker logo retention and softer facial detail on wide shots, so watch branded and character-consistent edits closely.

Runway launched Aleph 2.0 inside a new Edit Studio that lets users change one frame, preview it, and spread the edit across a whole video. The release gives web editors finer control than clip-by-clip regeneration.

Runway said it is opening a Tokyo office and investing an initial $40 million in Japan after tripling its enterprise customer base there in 12 months. It matters because Japan is already Runway's third-largest market, adding local hiring and sales capacity for media, gaming, and advertising teams.

Runway launched Runway Agent, a conversational tool that ideates and generates fully finished, sound-designed videos for ads, shorts, and social posts. Try it if you want end-to-end production inside one chat-driven workflow instead of clip generation alone.

Runway published the winners of its inaugural Big Pitch Contest for Shows That Don’t Exist Yet and released a reel of the top five projects, led by grand-prize pilot Sincitium. The package gives creators a clearer benchmark for AI-native pitches by showing finished pilots instead of isolated tool demos.

Runway launched Characters, a real-time system that turns one image into a conversational HD video agent. The company says replies start in 1.75 seconds and stream above 24 fps, so live avatar workflows are moving closer to production use.

Runway launched native mobile apps for both iOS and Android. The release moves its generation workflow onto phones instead of web and desktop sessions alone, so creators can test it on mobile.

Runway Big Pitch submissions like RE/START and Ghost Chasers are arriving as three-minute pilots with outtakes, extra scenes and plans for recurring episodes. Watch how far current AI film tools can stretch long-form coherence, since that remains the hardest part.

GPT Image 2 went live in Runway and Meshy, and users also reported PixPretty support plus new 4K size and quality controls in third-party interfaces. The rollout extends text rendering and layout control into app identity, brand boards, and infographic work.

Creators reported longer waits, 98 percent-end refusals, and weaker generations around Seedance 2.0, and a Runway-linked account said it was working with Bytedance on fixes. The slowdown matters because Seedance is simultaneously expanding through presets, omni-reference tests, and stacked workflows for ads and short films.

New demos showed Seedance 2.0 driving age-progression montages, battlefield time-freeze shots, still-sequence animation, and blockout-to-final-render VFX workflows across Mitte, Leonardo, Runway, and Comfy Hub. That matters because creators are using the same model for reference-driven clips, previs, and polished short-form outputs instead of one-off effect shots.

Creators published repeatable Seedance 2.0 recipes for time-freeze scenes, tracking shots, sports-broadcast surrealism, fantasy fly-throughs, and music visuals. Several threads included full prompts, reference-image setup, and timeline instructions, so use them as workflow templates rather than finished clip examples.

Runway opened a two-week Big Pitch contest for shows that do not exist yet, with $100,000 in prizes and a three-month plan discount. Creators can use Runway TV pitches as submission demos, giving AI show concepts a clearer commissioning path.

OpenArt users reported Seedance 2.0 now renders 1080p video with consistent real-human faces, and posts on Runway iOS and ComfyUI showed the higher-resolution model spreading to more surfaces. That widens access beyond yesterday's single-platform 1080p rollout.

Runway added 1080p output for Seedance 2.0, while Freepik shipped the same upgrade and Dreamina began phasing in 1080p downloads for paid users in several regions. Higher-resolution delivery is now available for the same model across major creator platforms.

Runway now lets a Character join video meetings from a pasted Zoom, Google Meet, or Teams link. The feature extends Runway Characters from rendered clips into live meeting stand-ins, so watch the launch demo and early reactions for reliability.

Runway said one creator finished a short ad in one afternoon, while others published 2-5 minute AI films and shared their stacks. The posts quantified longer production runs, from 398,055 Seedance credits across 113 scenes to multi-tool film pipelines.

Gossip Goblin released The Patchwright on YouTube after teasing a Seedance-built fantasy short. Creators are using Seedance stacks for multi-minute story scenes and even full-film planning.

Runway expanded Seedance 2.0 from Unlimited queues to every paid plan, and creator posts show new access on US accounts. Some users report human-face references now working there, while Weave tests and other creators still hit face blocks.

Freepik removed plan and region gates on Seedance 2.0, and Runway opened the model to all paid tiers. Posts about Higgsfield and MovieFlow also point to broader access and free trials, so creators can test availability across more platforms.

Creators showed Seedance 2.0 keeping the same voice across language and film-style changes, while others shared POV battle prompts, real-to-anime transitions, and rapid-cut sequences. These posts outline repeatable ways to control pacing, continuity, and reference-driven motion, so creators can borrow the workflows for short-form scenes.

Runway added prompt-generated custom voices for Characters in the web app and API. Creators can now define tone and persona from text instead of recording or cloning a source voice first, which should speed up voice setup.

Runway users report Seedance 2.0 now works on Unlimited plans with one-click upscale and node-based workflows. Early tests peg service limits at two concurrent jobs with 10–20 minute queues, so creators should watch throughput before relying on it for production.

Runway added Seedance 2.0 for text, image, video, and audio inputs on Unlimited and Enterprise tiers. CapCut also rolled Dreamina Seedance 2.0 into the U.S., but region gating, relaxed-style queueing, and face-reference issues still affect use.

Turkish creator Ozan Sihay released a seven-minute one-person AI short film built with Seedance 2.0, Kling 3.0, Nano Banana 2, Runway, HeyGen, Suno, and CapCut. The film matters because it turns Seedance’s weak face realism into a masked-character design rule and shows the planning graph behind the finished cut.

Summit attendees posted a preview of Firefly generating 3D objects from text, and creators also showed a Boards-based short-film pipeline built in Firefly. Try the workflow if you want one setup for asset generation, background removal, scene layout, and reference-driven animation.

New Multi-Shot demos showed Runway turning short prompts into 15-second dirt-bike chases, forest ambushes, and dialogue-led sequences. The examples make the web app easier to read as a prompt-to-scene tool, though evidence is still mostly creator-side tests.

Runway released Ad Concepter on the web app to generate ad concepts from a prompt, reference image, and product shot, then tied it to a contest with up to $100K in prizes. The tool makes concept ideation more turnkey, but users still need paid-plan access and the official watermark.

Runway's new web app turns a prompt or starter image into a cut scene with dialogue, sound effects and shot pacing. Creators can now block whole sequences instead of stitching isolated clips.