Releasesby GlyphFLUX 3 Video Agent Skills
Six new Agent Skills teach coding agents like Claude Code, Cursor, and Windsurf how to direct FLUX 3 video generations. flux-3-video , Routes a request to the skills it needs flux-3-prompt-doctor , Catches the decisions that change the payload before anything is generated flux-3-cinematic-inserts , Shot craft for text-to-video flux-3-keyframes-continuation...
Also shipped Aug 7, 2026Black Forest Labs in August 2026 →
DCM Projects (General availability)
DCM Projects are now generally available and are no longer in Preview . DCM Projects enable a declarative approach to managing Snowflake objects as code. You define the desired target state of your databases, tables, tasks, and other Snowflake objects in definition files, and Snowflake determines and applies the necessary changes to reach that state.
Snowflake Native Apps: Cortex Agents and MCP servers (General availability)
Cortex Agents and MCP servers in Snowflake Native Apps are now generally available. Providers can create the following objects in an app’s setup script: Apps can also use inter-app communication so that one app’s agent calls another app’s agent or MCP server.
Tag automations (Beta)
Tag automations are now in Beta . A tag automation assigns or removes governed tags on the Unity Catalog tables or volumes that match conditions you define, so tags stay accurate as your data and metadata change.
Change data feed on materialized views (Beta)
You can now read a change data feed from a materialized view created in a Lakeflow pipeline or in Databricks SQL, using Databricks Runtime 18 LTS or above. Use this to replicate materialized view changes to destinations outside Databricks, or to keep a history of materialized view changes for auditing and reporting.
ai_search function (Beta)
The ai_search() SQL function retrieves information from one or more AI Search indexes configured as knowledge sources. Given a natural-language query, the function generates optimized search queries, retrieves and deduplicates results across sources, reranks them by relevance, and returns the most relevant documents.
AlloyDB can sync BigQuery tables in preview
BigQuery tables can be synced into AlloyDB once or on a periodic schedule, giving operational analytics low-latency transactional access to data lake data.
More from FLUX APIEvery FLUX API release →
FLUX 3 , Video With Synchronized Audio
FLUX 3 is our first video model: one model trained across image, video, and audio, generating video with synchronized sound. Available now as a preview.
Key Features
- Up to 20 seconds at FHD (1920 × 1088 for 16:9), 24 fps, in a single request Synchronized audio , multilingual speech with strong lipsync, plus effects and ambience, generated with the frames Four modes on one endpoint , text to video ( t2v ), image to video with 1–10 pinned keyframes ( i2v ), video continuation ( v2v ), and draft enhance ( draft_enhance )...
Endpoint
POST /v1/flux-3-video The final polling response includes cost , the settled cost in credits for the request. See the FLUX 3 documentation to get started, and the pricing page for per-second rates. Video editing and Omni Reference with images and videos will be available soon.
FLUX MCP Server , Video Generation
The FLUX MCP server now generates video with FLUX 3, directly from Claude, Cursor, Codex, Windsurf, or any MCP-compatible client.
Key Features
- generate_video , Text to video, image to video from keyframes, and video continuation, with a prompt plus optional duration (5–20 seconds), aspect_ratio , and resolution .
FLUX 3 , Video Continuation Duration Limit
The maximum duration for video continuation ( v2v ) requests is now 15 seconds . Text-to-video, image-to-video, and draft enhance are unchanged at up to 20 seconds.
FLUX Video Upscale , 1080p, 2K, and 4K Video Super-Resolution
FLUX Video Upscale brings FLUX 3 powered super-resolution to video. Send a clip of up to 20 seconds and get it back at up to 4K, with the original audio track preserved.
Key Features
- 1.5×–3× upscaling , upscale_factor scales relative to the source resolution; the output keeps the source aspect ratio, capped at about 14.4 megapixels per frame Two modes , creativity: 0 (precise) preserves the source exactly and sharpens it, ideal for faces, products, and brand assets; creativity: 1 (creative, default) restores and invents fine detail...