Changelog

• Video Prompt Generator: New tool to create precise text-to-video and image-to-video prompts, guiding camera direction, style, pacing, and special effects for tailored AI video outputs.

• Seedream 3.1 Integration: Added support for Bytedance’s advanced text-to-image model, enabling high-quality, detailed image generation across diverse styles from descriptive prompts.

We are excited to announce the integration of Qwen Image, a cutting-edge image generation and editing model developed by Alibaba’s Qwen team. This feature enhances our platform with advanced capabilities for rendering complex text and generating high-quality images across various styles.

• Key Features:

  • Superior Text Rendering: Qwen Image excels at generating images with accurate, multi-line text in both alphabetic (e.g., English) and logographic (e.g., Chinese) scripts, ideal for posters, infographics, and slides.

  • Versatile Image Generation: Supports a wide range of styles, including photorealistic, anime, and minimalist designs, catering to diverse creative needs.

  Use Cases:

  • Create professional posters, infographics, and slides with precise text layouts.

  • Edit images with fine-grained control over style, content, and text.

  • Generate high-quality visuals for art, design, and storytelling.

Try Qwen Image here.

Veo 3 now supports seamless image-to-video creation. Flux Krea, a state-of-the-art text-to-image AI model developed with Krea and Black Forest Labs, generates photorealistic visuals with unique aesthetics, accurate textures, dynamic angles, and expressive colors, avoiding the typical “AI look.”

Wan 2.2 now supports text-to-video and image-to-video functionalities, enabling users to create dynamic video content from text inputs or static images with enhanced ease and flexibility.

Added a new AI image vectorizer that converts JPG and PNG files into high-quality SVG vector graphics automatically.

Google Veo 3 now supports 1080p text-to-video generation for high-quality, cinematic outputs.

Introduced a variety of new photo effect filters to transform images into unique styles, including Anime Filter, Baby Filter, Pixel Art Generator, Lego Filter, Ghibli AI Generator, Simpsons Character Creator, Photo to Painting, Photo to Sketch, Photo to Line Drawing, and Disney Filter.

Support Google Veo 3 Fast.

Support Flux Kontext Dev image editing.

Support Hailuo 2's text to video and image to video.

Support Pixverse 4.5's text to video and image to video.

Support Bytedance's text-to-image Seedream 3 and text/image-to-video Seedance 1.

Support for generating images using Imagen 4 Fast and Imagen 4 Ultra.

Support for the AI image-to-video generator.

Support for the AI video generator using Google Veo 3.

Support for image editing with Flux.1 Kontext.

Support for generating images using the new Imagen 4 model.

Support for editing images using the HiDream E1 model.

Support for generating HiDream-I1 Full model.

Support for generating HiDream-I1 Dev model.