What's new

• MomentFlow v5 and MomentFlow v5 Fast now support attaching a video file as a reference.
• A reference video helps preserve motion and style from the source clip, for example when you want to continue a video.

• Improved the quality of TTS generation.
• Reduced the number of incorrect and empty results.

WaifuStudio v2.6 update has been released.

What's new:

• Fixed issues with color tone mismatches between characters and backgrounds. Characters no longer look like they were cut out of a different anime and pasted onto a random background.
• Added flexible character age adjustment. If the default age doesn't work for you, you can use the prompts (aged up:1.0–2.0) or (mature female:1.0–2.0) at the beginning of your request and dial in the desired value.

A small but welcome update — especially the color fix, which previously could ruin even good generations.

Framy has been updated to version 1.5, and this is no cosmetic patch — it's a major engine upgrade.

What's New

Image Quality

The latent space has been rebuilt with an updated VAE trained on higher-quality data. In practice this means: hair finally looks like hair, text is legible, and fine facial details no longer dissolve into mush. Visual artifacts have been noticeably reduced.

Audio Out of the Box

Framy 1.5 generates synchronized audio in a single pass — dialogue, ambience, sound effects. An updated vocoder has improved speech intelligibility, and cross-modal alignment has reduced lip-sync and timing drift.

Motion and Consistency

The image-to-video mode has been significantly improved: fewer "frozen" frames, fewer spontaneous panning shots, and better preservation of the source image's visual integrity.

Native Vertical Video

For the first time, vertical generation up to 1080×1920 is supported — the model is trained on portrait data rather than cropping from landscape. Reels and Shorts can now be fed directly.

The text encoder has been scaled up 4×, making the model significantly better at understanding complex prompts describing camera angles, character movements, and scene composition.

Prompt Enhancer

Another major bonus is a powerful prompt enhancer. It helps turn a rough request into a more precise and expressive scene description, carefully refining motion, camera angles, dialogue, and atmosphere so the final video lands closer to the original idea on the first try.

In short, Framy 1.5 is one of those cases where the version number is being modest.

We've rolled out an update to our image-to-video generation model — WildClips v3.6.

Key changes:

• Seamless transitions: transitions between 5-second clips are now smooth. No more visual "stutters" at the cuts.
• Improved dynamics: objects in the frame move noticeably more naturally.
• Smart prompt assistant: the system has learned to analyze the input image to automatically fine-tune your text prompt to perfection. The neural network now better understands what you want to achieve, even if you're a bit unsure yourself.

The update is already available. Let's go test it out!

A new image generation and editing model is now available in our chat — Nano Banana 2 (powered under the hood by Google's Gemini 3.1 Flash Image).

What's new and why it's cool:

• Significantly cheaper: Generation has become much more affordable compared to the previous version. This is the case where quality goes up and the price goes down — an economy we like.
• High speed: The model delivers a finished result in an average of 10–15 seconds without losing quality. Time is money, and fast neural bananas are a double win.
• Perfect text: Excellent at generating typography and readable text in different languages directly on images. Ideal for mockups and presentations.
• Frame stability: Confidently maintains facial consistency (up to 5 characters) and preserves the details of complex scenes (up to 14 objects).
• Advanced logic: The model better understands complex multi-layered prompts and can rely on up-to-date data from the web.

Jump into the chat and test the new feature. It's a great tool for tasks that require a strict balance between speed, production quality, and a nice price.

Meet Furry Master v4 — a major upgrade for those crafting anthropomorphic heroes. We’ve traded the old versions for this powerful fourth-generation tool to take your generations to the next level.

Why Furry Master v4 is mastery without the air quotes:

• Anatomy Without the Surprises: The model has learned to properly handle paws, tails, and complex poses. Your heroes will no longer look like they just escaped a funhouse hall of mirrors.
• Texture Breakthrough: Incredible detail on fur, scales, and accessories. Every single hair is in its place — perfectionists, rejoice.
• Seamless "Cleaning": Version v4 plays beautifully with our editing tools. Removing an unwanted object or touching up the background is now possible without sacrificing the quality or style of the main image.
• Understands You (Finally): Enhanced comprehension of complex prompts allows for more precise rendering of lighting, atmosphere, and the fine nuances of your creative vision.

We are expanding our visual content capabilities and adding support for the Google Nano Banana Pro model.

New features are now available to you directly in the chat interface:

• Image generation: create graphics from scratch using text descriptions.
• In-dialog editing: make changes and refine images directly while chatting with the model.

This update allows you to work with images faster and more conveniently without leaving the familiar chat window.

• Improved color correction: colors are more accurate, cleaner, and more natural.
• Increased detail: finer elements and textures are rendered more thoroughly.
• Updated post-processing algorithms: images look higher quality right out of generation.
• Reduced generation cost.

• Faster generation
• Fewer artifacts
• Reduced cost
• Improved tag handling and updated documentation