News — Models & Product Updates

Choose Prime when a faster Wan 3.0 result is worth the higher credit cost.

Create text-led visuals or edit images with written instructions and up to three ordered references.

H3 Max Lip Sync is now the short-clip image model in Talking Head. It animates a still portrait to match spoken audio through fal.

DayGen Agent and Direct can now plan with DeepSeek V4.1 Flash, GLM 5.3 Flash, and Kimi K3.

GPT Image 2.5 replaces GPT Image 2 as DayGen's default OpenAI image model.

Lyria 3.5 is the default Lyria model for new full songs in DayGen.

fal’s H3 Max Turbo brings the H3 Max look into a faster, lower-cost video workflow with native synchronized audio.

One consistent filtering experience across Gallery, Explore, folders, and media pickers.

Browse public creations from two models side by side in Explore.

Google’s stable Gemini Omni video model brings native audio, ordered visual guidance, first-to-last-frame interpolation, and replayable edits into one DayGen workflow.

Use Meta’s image model for precise creation, prompt-directed edits, and multi-reference composition through FAL.

Enhance a private video with Runway Magnific while keeping its DayGen source and ownership lineage intact.

Use deeper thinking, direct an image with one authorized video, or make a one-time grounded result with Web and Image search.

Create up to 30 seconds of video from text, precise start and end frames, or a mixed reference set—with native sound in the same generation.

Inspect progress, provide missing input, and steer or continue a run without starting over.

Create new images or direct precise multi-image edits with xAI’s latest image model, now replacing the previous Grok image endpoint throughout DayGen.

Turn a musical brief into a complete vocal or instrumental song with MiniMax Music 3.0.

Create polished imagery or make precise changes to an existing image with Microsoft AI’s Standard and Pro models, hosted through FAL.

Manage Films in a dedicated library, edit on the timeline, save versions, and export in the background.

Plan longer, more ambitious creative work with xAI's frontier model in Agent and Direct.

Turn a prompt, a frame pair, or a short audio clip into fast, high-resolution video with LTX 2.5.

Create cinematic video with FLUX 3, alongside five FLUX.2 models for high-resolution image generation and editing.

Create longer, reference-rich video with frames, images, video, audio, and native sound.

MiniMax H3 creates fixed-2K video from a required prompt plus either first/last frames or up to 12 mixed references. Its reference mode supports up to nine images, three videos, and three audio clips within that shared limit.

Grok Imagine 1.5 is DayGen's Grok model for new video generation. Start from text, animate one still, or guide a clip with two to seven visual references while keeping native audio.

Reve 2.1 Layout separates composition from rendering so follow-up edits can preserve and reshape the image structure. Use it for posters, editorial layouts, controlled scenes, and iterative composition work.

A durable conversational workspace that plans and creates across DayGen.

Create detailed 2K or 4K images with strong consistency across multiple references.

Create styled raster images from an editorial library of ready-made visual looks.

Organize shared work into projects with member access and project-level assets.

Generate new clips or continue from a source video with image guidance.

Fast 1K image generation and editing with a generous visual-reference window.

Create lower-cost Veo video with native audio in a focused create-only model.

Create lower-cost multimodal Seedance video with frames and audio guidance.

Create and edit video with ordered visual references and character-aware guidance.

Generate or restyle video from text, images, start and end frames, or a source clip.

Explore creative image directions with style references and adjustable visual controls.

Create text-forward images, posters, logos, and graphic layouts with remix guidance.

Create consistent images from reference-heavy prompts and visual direction.

Translate spoken video into one or more languages from one focused workspace.

Create, organize, and share work with your team in one dedicated workspace.

Create clean raster graphics, icons, and brand-ready design assets.

Create and edit cinematic images with multimodal reference guidance.

High-fidelity image generation and editing with richer output controls.

Create multimodal video with frames plus image, video, and audio references.

Animate images and continue clips with frame guidance and optional synchronized audio.