Changelog

Latest updates and improvements to the platform

October 14, 2026

Nano Banana 2.1 Is Now Available

Nano Banana 2.1 brings sharper text, stronger prompt adherence and more consistent subjects to image generation and editing, at 1K, 2K and 4K.

October 13, 2026

Gemini 4 Argon

Gemini 4 Argon, Google's new flagship reasoning model, joins the creative authoring picker.

October 13, 2026

Ideogram 4.5

Accurate typography and precise edits with Ideogram 4.5.

October 11, 2026

Claude Sonnet 5.5

Claude Sonnet 5.5 is now available for creative authoring and text generation.

October 11, 2026

GPT-6.1 Sol and GPT-6 Luna

GPT-6.1 Sol is now featured for creative authoring, and GPT-6 Luna joins the OpenAI model list.

October 11, 2026

GPT Image 2.5 Flare and Sunburst

Generate with Flare or choose Sunburst for precise edits, powered directly by the OpenAI API.

October 11, 2026

Grok Imagine Video 1.5 text and reference

Start Imagine Video 1.5 from a prompt or from up to seven reference images, with audio included.

October 10, 2026

FLUX 3 Image

FLUX 3 Image is now available for generation and editing, with stronger text and local edits that take the source image plus up to nine reference images.

October 10, 2026

Claude Haiku 5.5

Claude Haiku 5.5, Anthropic's fastest and lowest-cost model, is now available by model id.

October 9, 2026

Gemini 3.8 Flash

Gemini 3.8 Flash is now the default authoring model, at the same speed and cost as 3.7.

October 9, 2026

Claude Fable 5.1

Claude Fable 5.1, Anthropic's most capable model, is now available as a premium option in the advanced model picker.

October 4, 2026

Data sheets and personalized creative sets

Data sheets are rebuilt with versions, typed columns, and a key column, and a layered static ad or rich media ad can now become one personalized ad per sheet row.

September 28, 2026

Eleven v4 for video voiceovers

ElevenLabs' Eleven v4 is now the default voiceover model for video ads, in the editor and in AI-generated video ads, and brings 11 new voiceover languages.

September 25, 2026

GPT-6 Astra and Claude Opus 5.5

OpenAI's GPT-6 Astra and Anthropic's Claude Opus 5.5 flagships are now available as LLM options, and Opus 5.5 is the new default reasoning model.

September 17, 2026

Visual Style is gone — describe the look in Additional Direction

The Visual Style dropdown and the video_style API/MCP parameter have been removed. Video generation always autodetects the look, and a specific style is now requested in plain language.

September 9, 2026

Grok Imagine Image 2.0 Is Now Available

Generate and edit stills with xAI's Grok Imagine Image 2.0 — 1K or 2K, low or medium quality, and up to three total input images (source + 2 extras).

September 8, 2026

Gemini Omni 1.1 Flash: 360p Drafts, 4K Masters, and Scene Extension

Google's Omni video model steps up to 1.1 — pick 360p through 4K, interpolate between a first and last frame, and extend a clip by 10 seconds.

September 5, 2026

Muse Image

Meta's Muse Image is now available for generation and editing—faithful instruction-following, accurate text, and $0.013 per image.

August 26, 2026

Gemini 3.7 Flash

Google's newest Flash workhorse is now available as the default LLM with promotional intro pricing.

August 26, 2026

Alibaba Wan 3.0 & Wan 3.0 Prime

Wan 3.0 lands in the video picker with text-, image-, and reference-to-video, native audio, and clips up to 30 seconds.

August 7, 2026

Dreamina Seedance 2.5 video models

Seedance 2.5 brings coherent 30-second clips, up to 50 multimodal reference assets, audio-only references, and native multilingual speech to the video toolset.

August 1, 2026

Claude Opus 5 and Sonnet 5

Anthropic's Claude Opus 5 flagship and Sonnet 5 balanced models are now available as LLM options.

August 1, 2026

MiniMax Hailuo 03 (H3) Video Models

Hailuo 03 (H3) and Hailuo 03 Reference bring MiniMax’s frontier 2K video model to AdGreetz — text-to-video, image-to-video, and multimodal reference-to-video.

August 1, 2026

Krea 2 Turbo + Large Are Here

Krea 2 Turbo and Krea 2 Large are now available for text-to-image generation — rapid ideation and flagship aesthetics from Krea.

July 22, 2026

Happy Horse 1.1 Video Models

Happy Horse 1.1 and Happy Horse 1.1 Reference are now available with extended aspect ratios and enhanced video generation quality.

July 22, 2026

Seedream 5 Pro Is Here

Seedream 5 Pro is now available for image generation and editing with premium quality and enhanced reference image support.

July 21, 2026

Gemini 3.6 Flash and 3.5 Flash-Lite

Google's newest Flash workhorse and fastest Flash-Lite model are now available as LLM options.

July 4, 2026

Seedance 2.0 Mini: ByteDance's Cheapest Cinematic Video Tier

Seedance 2.0 Mini lands in the video model picker — image-to-video and reference-to-video with native audio at under two-thirds the price of the Fast tier.

July 3, 2026

Nano Banana 2 Lite and Gemini Omni Flash Are Here

Google's fastest image model and its new conversational video model land in the model pickers on day one.

June 23, 2026

MiniMax Hailuo 2.3 Video Models

Hailuo 2.3 and Hailuo 2.3 Fast replace Hailuo 02 with improved motion, consistency, and faster image-to-video iteration.

June 23, 2026

PixVerse V6 and V5.6 on Replicate

Generate cinematic PixVerse videos with multi-shot mode, native audio, and first/last frame transitions.

June 23, 2026

Runway Gen-4.5 Is Now Available

Generate cinematic text-to-video clips with Runway's top-ranked Gen-4.5 model on Replicate.

June 17, 2026

Grok Imagine Video 1.5 Is Now Available

Animate still images into short, audio-synced videos with xAI's new Grok Imagine Video 1.5 model.

May 25, 2026

Recraft V4.1 Is Now Available

We’ve added new Recraft V4.1 image and vector models to help teams move from fast concepting to high-fidelity final assets.

May 6, 2026

Happy Horse Video Models

Happy Horse and Happy Horse Reference are now available for faster, higher-quality video creation with text, image, and reference-driven workflows.

May 6, 2026

Happy Horse Video Edit

Edit existing videos with Happy Horse using prompt-based changes, optional reference images, and audio control.

May 2, 2026

GPT Image 2 on FAL

OpenAI GPT Image 2 is now available for text-to-image, reference-based image editing, and static ad generation through FAL.

April 12, 2026

PixVerse C1 Transition on fal.ai

New video model for cinematic transitions between two keyframes with optional native audio, 360p–1080p output, and 1–15 second clips via fal.ai.

April 12, 2026

Kling V3 Omni Video on Replicate

Unified multimodal video generation with reference images, video editing, native audio, and multi-shot control via Replicate.

April 9, 2026

PrunaAI P-Image Upscale

Adds PrunaAI P-Image Upscale — a fast, efficient image upscaler supporting outputs up to 8 MP with 2x and 4x scaling.

April 9, 2026

Wan 2.7 R2V Model Integration

Alibaba's Wan 2.7 Reference-to-Video is now available for reference-driven video generation with subject identity preservation, up to 7 reference images, 2-10 second durations, and 1080p output.

April 8, 2026

Qwen Image Edit Plus and Recraft V4 family

Adds Qwen Image Edit Plus for multi-image editing, plus Recraft V4 raster, V4 Pro, V4 SVG, and V4 Pro SVG text-to-image models.

April 8, 2026

Veo 3.1 Lite Model Integration

Google Veo 3.1 Lite is now available as the fastest and most affordable Veo model, with text/image-to-video generation and optional synchronized audio.

April 8, 2026

Wan 2.7 Image and Wan 2.7 Image Pro

Adds Alibaba Wan 2.7 Image models for text-to-image, multi-reference generation, and image editing with up to nine reference images.

March 24, 2026

Grok Imagine R2V Model Integration

xAI Grok Imagine R2V is now available for reference-to-video generation with up to 7 reference images, 1-10 second durations, and multiple aspect ratios.

March 11, 2026

Background Removal Tool

Instantly remove backgrounds from any image with Pixelcut's AI-powered background removal. Perfect for e-commerce product photos, marketing assets, and creative workflows.

March 9, 2026

LTX 2.3 Pro & Fast Video Models Now Available

LTX 2.3 Pro brings camera motion control, last-frame interpolation, retake and extend capabilities, up to 4K resolution, and synchronized audio. LTX 2.3 Fast offers the same features with faster generation at up to 20 seconds duration.

February 27, 2026

PrunaAI P-Video Model Now Available

P-Video is now available for video generation, delivering fast text-to-video and image-to-video creation at 720p and 1080p resolution with durations from 1 to 10 seconds.

February 26, 2026

Nano Banana 2 Is Now Available

Nano Banana 2 is now available for image generation and static ad workflows, delivering faster high-quality outputs with broader aspect ratio support for modern creative formats.

February 24, 2026

Seedream 5 Lite Is Here

Seedream 5 Lite is now available across image generation, image editing, and static ads with stronger prompt understanding, cleaner compositions, and better creative consistency.