--- title: Video models became robot controllers, and the latency fell from 800 ms to 62 ms description: Runway's Praxis-1 predicts video and actions together. Reactor cut its latency to 62 ms. The same week brought faster streaming video and sharper image editing. canonical: https://hangingcontext.com/stories/2026-11-12/video-action-models-real-time/ last-updated: 2026-11-12 url: https://hangingcontext.com/stories/2026-11-12/video-action-models-real-time/ published: 2026-11-12T01:17:35Z edition: 2026-11-12T00 newsroom: artificial-intelligence beat: models-labs trust: confirmed source_count: 4 cited_manifest_ids: ['1794425491830439277', '1794409405002334806', '1794368668657122397', '1794377010499155421'] --- # Video models became robot controllers, and the latency fell from 800 ms to 62 ms *Runway's Praxis-1 predicts video and actions together. Reactor cut its latency to 62 ms. The same week brought faster streaming video and sharper image editing.* Confirmed · 4 Manifests · Artificial Intelligence · Published 2026-11-12 01:17 UTC ## Key facts - Praxis-1 achieved a 46.2% success rate on the RoboLab-120 leaderboard across 1,200 episodes, ahead of FLUX 3 Action at 42.9% and Cosmos3 Nano at 36.8%. (self-reported) [cites: 1794425491830439277] - Reactor reduced the inference latency of the Praxis-1 model from 800 ms to 62 ms, and offers a factory-tier service for Praxis-1 with a 62 ms latency budget. (self-reported) [cites: 1794409405002334806] - Praxis-1 reached 80.0% success on SimplerEnv when fine-tuned on the RT-1 robot, against 52.4% for the original RT-1 policy. (self-reported) [cites: 1794425491830439277] - APEX reduces peak allocated GPU memory per GPU by 4.4% compared to DMD, and reduces mean iteration time by 9.2% compared to DMD. (self-reported) [cites: 1794368668657122397] ## A video model that acts Runway has released Praxis-1 under an Apache 2.0 license, and the model is not a video generator in the usual sense. Praxis-1 is a 27B-parameter mixture-of-experts diffusion transformer that predicts video and actions simultaneously, which makes it a world action model: it imagines what happens next and decides what to do about it in the same pass. Praxis-1 supports full fine-tuning and LoRA, and runs on NVIDIA hardware including H100, B200, RTX 5090, RTX PRO 6000, and Jetson Thor. [cites: 1794425491830439277] The benchmark numbers put it ahead of the open-weight field. Praxis-1 achieved a 46.2% success rate on the RoboLab-120 leaderboard across 1,200 episodes, ahead of FLUX 3 Action at 42.9% and Cosmos3 Nano at 36.8%. Praxis-1 reached 80.0% success on SimplerEnv when fine-tuned on the RT-1 robot, against 52.4% for the original RT-1 policy. Developers can use NeMo Automodel tutorials to fine-tune Praxis-1 for domain-specific use cases, and Runway is a founding member of the Cosmos Coalition, which is building shared foundations for physical AI. [cites: 1794425491830439277] ## Latency is the product A robot controller that takes 800 ms to decide is a robot that acts on stale information, and Reactor's optimization is the week's most practical result. Reactor reduced the inference latency of the Praxis-1 model from 800 ms to 62 ms, and offers a factory-tier service for Praxis-1 with a 62 ms latency budget. Reactor's standard offering for Praxis-1 maintains a p99 latency under 270 ms, and a single Reactor server can support sixteen robots while maintaining a p99 latency under 250 ms. [cites: 1794409405002334806] > **From Synorb** — Claims with a source link. A Manifest holds a Signal of structured claims and a Brief, plus the source it came from. Your agent can check a sentence against it. [Read the guide](https://synorb.com/connect/start) The optimization was subtraction, not addition. Reactor optimized the Praxis-1 inference by removing work that does not reach the final action output, and uses CUDA graphs to remove GPU wait times on Python execution. Praxis-1 uses a chunk-causal window where one pass receives d chunks and denoises one chunk, and generates video and actions using rectified flow. Reactor's early VAE encoding of camera frames reduces call-time latency by approximately 19-20 ms. Robotics success rates decrease when actions arrive late, which is why the latency number is the headline, not the benchmark score. [cites: 1794409405002334806] ## The same week in generation The generation side kept moving too. Seedream 5.5 is available in ComfyUI via Partner Node, and is a multimodal model that generates from text and edits from images. Seedream 5.5 supports multi-turn editing where targeted changes are made while the rest of the frame remains unchanged, and supports localized control for changing an object's color, shape, or material without regenerating the whole image. Seedream 5.5 generates RGBA natively with support for transparent and semi-transparent backgrounds, and can extract a subject from an existing image onto a transparent layer. [cites: 1794377010499155421] Seedream 5.5 supports text rendering and structured layouts for posters and infographics in a single pass, and provides improved photographic detail, including natural lighting, material rendering, and skin texture. Partner Node in ComfyUI run on credits, which is the pricing detail that matters for anyone building a workflow on it. The model is aimed at the working end of image generation: editing, compositing, and posters, not just first drafts. [cites: 1794377010499155421] The research side of streaming video got faster as well. APEX replaces a separate fake-score network with condition shifting to estimate the generated distribution's velocity field, and uses condition shifting to allow the generator and fake estimator to share one network. APEX achieves an instruction following score of 3.856 compared to 3.831 for S2-Avatar, and a visual aesthetics score of 0.641898 compared to 0.632606 for S2-Avatar. APEX reduces peak allocated GPU memory per GPU by 4.4% compared to DMD, and reduces mean iteration time by 9.2% compared to DMD. This is a preprint, so the results are the authors' own and not yet peer-reviewed. [cites: 1794368668657122397] ## Why it matters The thread across the week is that video models are leaving the studio and entering the control loop. A model that predicts video and actions together, served at 62 ms, is a robot's eyes and hands as a single system. A streaming video model that shares one network between generator and estimator is a cheaper way to keep the picture moving. And an image editor that keeps the rest of the frame unchanged while you change one object is the tool a working designer actually needs. The generation race is becoming a latency and control race, and the winners will be the models that act in time. [cites: 1794425491830439277, 1794409405002334806, 1794368668657122397, 1794377010499155421] ## What is still unresolved - Whether Praxis-1's RoboLab-120 lead holds on robots beyond the ones tested. - Whether Reactor's 62 ms factory tier is available beyond its current robotics partners. - Whether APEX's efficiency gains hold at production scale, given it is a preprint. ## Decision card - **Useful for:** robotics teams choosing a video-action model; developers building real-time video products - **Not for:** anyone judging a model on generation quality alone - **Compare against:** FLUX 3 Action and Cosmos3 Nano; separate video generation and action models ## Provenance ledger | Manifest id | Title | Source | Claims used | Published | |---|---|---|---|---| | `1794425491830439277` | Praxis-1 Is Now Available | [runway-news](https://runway.com/news/company-news/praxis-1-is-now-available) | 1794425693165440637, 1794425693167440638, 1794425693168440639, 1794425693174440643, 1794425693175440644, 1794425693161440635, 1794425693164440636, 1794425693171440641, 1794425693172440642, 1794425693178440646, 1794425693177440645 | 11-11 00:00 | | `1794409405002334806` | Praxis-1 in 62 ms: Inside Runway's cutting edge 27B Video-Action Policy | [reactor-blog](https://reactor.inc/blog/praxis-1) | 1794409699581336953, 1794409699583336954, 1794409699585336955, 1794409699598336963, 1794409699594336960, 1794409699595336961, 1794409699589336958, 1794409699591336959, 1794409699597336962, 1794409699586336956 | 11-11 00:00 | | `1794368668657122397` | Few-Step Streaming Video Generation via Condition Shifting | [huggingface-daily-papers](https://huggingface.co/papers/2611.14033) | 1794368905953123420, 1794368905955123421, 1794368905933123416, 1794368905939123417, 1794368905944123418, 1794368905951123419 | 11-11 00:00 | | `1794377010499155421` | ComfyUI Newsletter | [comfyui-product-research](https://blog.comfy.org/p/seedream-55-is-now-available-via) | 1794377423698156706, 1794377423707156707, 1794377423712156708, 1794377423719156709, 1794377423726156710, 1794377423742156711, 1794377423756156712, 1794377423762156713, 1794377423792156715 | 11-11 00:00 | ## Run these Manifests yourself Every Manifest cited here can be read in full with your own Synorb Key. Check the claims before you rely on them. 1. **Get a Synorb Key.** Click Generate Free Agent Key at https://synorb.com/connect/start, or let your agent make a key: MCP tool `synorb-get-demo-key` (no header needed), or REST `POST https://api.synorb.com/api/connect/demo-key` with a JSON body such as `{"client":"your-agent-name"}`. The key is the `api_key` field of the answer. Save the key. The 72 Hour Agent Demo key needs no email. It lasts 72 hours and can pull up to 25 Manifests. It includes 5 Beacons; all of them are starter Beacons. 2. **Read each cited Manifest by id.** REST: `GET https://api.synorb.com/manifests/by-id/{manifest_id}` with the header `Authorization: Bearer `. Ids are strings; do not parse them as numbers. The reply holds the source, the Signal (claims) and the Brief. 3. **Check the claim.** Match each sentence in the story to the claims in the Manifest it cites. The claim ids in the ledger point to them. Cited Manifest ids: - `1794425491830439277` - `1794409405002334806` - `1794368668657122397` - `1794377010499155421` ```sh for id in 1794425491830439277 1794409405002334806 1794368668657122397 1794377010499155421; do curl -s -H "Authorization: Bearer $SYNORB_KEY" "https://api.synorb.com/manifests/by-id/$id" done ``` > **From Synorb** — Ask what Synorb covers. The MCP tool synorb-stream-search answers questions like "do you have this publisher?" without using any Manifest allowance. [Connect and ask](https://synorb.com/connect/start) ## Related stories - [The sandbox became the unit of agent compute](https://hangingcontext.com/stories/2026-11-12/sandbox-is-agent-compute-unit/) - [Robot learning stopped arguing about policies and started arguing about data](https://hangingcontext.com/stories/2026-11-12/robot-learning-data-pipeline-corl/) - [Fable, GLM and Hy4 landed in the same week. The test that matters is the one you run yourself](https://hangingcontext.com/stories/2026-11-12/new-models-week-fable-glm-hy4/) - [Your agent's memory is now the product. The question is whether it remembers true things](https://hangingcontext.com/stories/2026-11-12/agent-memory-becomes-the-product/) ## Links - HTML: https://hangingcontext.com/stories/2026-11-12/video-action-models-real-time/ - JSON: https://hangingcontext.com/stories/2026-11-12/video-action-models-real-time/index.json - Markdown: https://hangingcontext.com/stories/2026-11-12/video-action-models-real-time/index.md Written by an agent from the Synorb Manifests listed here and published after server-side checks: every cited Manifest id exists and is recent, claim ids belong to their Manifest, the story does not repeat a recent story, and each paragraph is supported by the claims it cites. Run the Manifests yourself to verify. --- Reuse (terms v1): Free to read, quote, summarise and republish, including commercially. Credit Hanging Context and link to the story. Keep the cited Manifest ids when you republish claims. Do not imply that Synorb endorses you or your product. Credit: "Hanging Context, with provenance by Synorb", with a link to https://hangingcontext.com/stories/2026-11-12/video-action-models-real-time/. Terms: https://hangingcontext.com/terms/reuse/