Changelog
Follow up on the latest improvements and updates.
RSS
new
Image Generator
Added Public Styles to FLUX.1 [dev]
We’ve added 5 public styles to the Image Generator. Previously, styles were only available through custom training in the Model Trainer. These new styles are ready to use in FLUX.1 [dev] and are available to all users, including those on the free plan.
New styles:
- Analog
- Portrait
- Polaroid
- VHS Glitch
- Neon Lights
Styles can be applied directly without training and help give generated images a distinct visual look.
Available now in the Image Generator.
new
Video Generator
New video generation model: Kling 2.1
Kling 2.1 is now available in the Video Generator in three versions:
- Kling 2.1 Standard:720p · 5s & 10s · Image to Video · All aspect ratios
- Kling 2.1 Pro:1080p · 5s & 10s · Image to Video · All aspect ratios
- Kling 2.1 Master:1080p · Text to Video & Image to Video
Kling 2.1 is optimized for high-quality video generation with excellent format flexibility.
new
Image Generator
New model in Image Generator: FLUX.1 Kontext [pro]
FLUX.1 Kontext [pro] is now available in the Image Generator. It's made for text-based image edits.
You can use it with a reference image to edit visual or textual elements of the input by describing desired changes in natural language. It’s a smart, multimodal model built for clear, accurate edits with minimal latency.
new
Image Editor
New feature in Image Editor: Text Editing
We’ve added FLUX.1 Kontext [pro] to the Image Editor as a new feature: Text Editing.
This model allows you to make local edits to an image based on text prompts. It’s fast, consistent, and understands both text and visual content — ideal for precise edits and creative control.
new
improved
Image Generator
Added Image References to GPT Image and FLUX.1.1 [ultra]
Image References are now supported in GPT Image, GPT Image HD, and FLUX.1.1 [ultra].
- GPT Image & GPT Image HD -Supports up to 3 reference images. The model combines them into one composition. Ideal for images that include multiple elements and require clear text.
- FLUX.1.1 [ultra] -Supports 1 reference image. The model uses it to guide generation based on visual style or structure. Delivers ultra-sharp 2K images.
Available in the Image Generator.
new
New pricing
We introduced a new pricing with 1 subscription plan - Pro.
Key information:
- Starts at $6/month
- One subscription plan: Pro, with 11 credit tiers to choose from
- Access to all tools and features - your credits balance is the only limit
- Prices now include taxes
Additionally, we lowered image generation costs. Prices that were 6, 12, or 60 credits are now 5, 10, and 50 — across all plans.
This versatile model is optimized for generating graphics with clear, readable text. It’s particularly well suited for infographics, editorial layouts, slide content, UI designs, and educational diagrams.
Comes with two quality tiers – Medium and High.
GPT Image 1 is now available in the Image Generator.
Introducing MAGI-1, the latest addition to the Video Generator.
Key advantages include:
- Excellent motion and video quality
- Strong understanding of prompts
- Low cost
Available in Video Generator
improved
Video Generator
Video Generator update
We’ve introduced two major updates to the Video Generator:
1. Redesigned interface
The Video Generator interface has been fully rebuilt to provide a more intuitive and streamlined user experience.
2. New video generation models
Six advanced video models have been added, offering a range of options for aspect ratios, video length, resolution, and frame rate.
Available models:
- Google Veo 2
- Runway Gen-4 Turbo
- Runway Gen-3 Turbo
- Kling 2.0 Master
- Kling 1.6 Pro
- Kling 1.6 Standard
- Minimax 01
Read guides here.
Use Video Generator here.
new
improved
Image Generator
New Image References for Flux [dev] and improved Model Trainer
We've added two new Image References to Flux [dev]:
1. Hard edges
- Perfect for preserving objects and original image composition while changing the style.2. Depth
- Perfect for generating images with the same depth as the original image.Image references also work with Model Trainer Characters and Styles, meaning you can combine your reference images with your custom-trained models.
Additionally, we’ve improved the Model Trainer’s training process. It now gives better results with longer, more creative prompts – and delivers more photorealistic and diverse images from shorter ones.

Load More
→