> ## Knowledge Base Index
> Fetch the complete knowledge base index at: https://help.seelab.ai/sitemap.xml
> Use this file to discover available pages before exploring further.
> Pure-Markdown content can be obtained by appending a '.md' suffix to the content URLs listed in the sitemap (without the trailing slash).

# Changelog

# **2026-09-08**
###### Video
Videos in the Videos page now load and play more smoothly, for a better browsing experience.
###### 
Model builder
You can now include a brief when creating a custom model, making it easier to give context and guidance right from the start.


# **2026-09-03**
###### Global
We've simplified how credits work on Seelab. Image and video credits are now unified into a single credit pool.
**What's changing:**
* Your video credits have been automatically transferred into your image credits — no action needed on your end.
* One credit balance now covers both image and video generation.
* Your total available credits remain the same; only the way they're organized has changed.
###### 
# **2026-09-02**
###### Model builder
Creating a custom model is now faster! It takes just a few seconds to a few minutes. 

# **2026-09-01**
###### Downloads
Multi-file streaming downloads are now available across the entire app, for faster and more reliable exports.

###### Composer
Layers can now go up to 4096px (previously limited to a smaller size).

###### Home Page
Fixed a bug where the link to the video tool wasn't redirecting to the correct dedicated page.

# **2026-08-26**
###### Video
**Generate from a custom model**
You can now generate videos directly from your custom models, for creations that stay true to your product identity or characters.

###### Editor
**Deleting generation history**
Fixed a bug that prevented deleting items from the generation history in the editor.

###### Resource Hub
**New filters**
Find your resources more easily with new filters by content type and originating workflow.

###### Collections
**ZIP downloads**
Downloading collections as ZIP files is now more reliable (no more memory-related crashes), with new controls added for a better experience.

###### Creation
**Detailed error messages and quick retry**
When a generation fails, a detailed error message now appears along with a retry button, so you can relaunch generation instantly without starting over.

###### General
**Handling of overly long prompts**
Pasted prompts that exceed the allowed limit are now automatically truncated, with a clear warning message.

# **2026-08-13**

**🎬 New: AI Video now has its own dedicated space**
Video generation is no longer tucked inside the Editor — it now lives in its own **Video** tab in the main navigation, with a workspace built specifically for it.
**What you can do:**
* **Prompt-to-video and image-to-video** in one panel — upload a **start frame** and, optionally, an **end frame**, and let the model animate the transition between them.
* **Full control over your render**: pick the AI engine, choose your **format** (16:9 or 9:16), **resolution** (720p or 1080p), **duration**, toggle **audio** on/off, and generate up to **4 variations** at once.
* **Camera presets** to apply ready-made camera moves instead of describing them in the prompt.
* A **searchable history feed** for everything you generate — filter by date or model, switch between list and grid view, and select multiple items at once.
![](https://storage.crisp.chat/users/helpdesk/website/-/6/8/0/3/6803ea00be5f5800/image_1sxkqtv.png =668xauto)

**🛠️ Fixes & improvements**
* **Fixed:** media preview modals could sometimes fail to open or close correctly.
* **Fixed:** resizing/downsizing images in the Editor caused a loss of image quality.
* **Fixed:** newly added images could unexpectedly be removed from the grid on the Creation page.
* **Improved:** the app update banner now checks for missing modules/files, so it reliably reappears whenever a new update is available.
* **New:** prompt fields now support up to 3,000 characters.

# **2026-07-21**

###### Creation
Fixed some display bugs that occurred while error generation

###### Global
Improve performance of some app parts

# **2026-06-08**

###### Creation
Added the ability to select an output resolution and quality 
Fixed some display bugs that occurred while waiting for a generation

# **2026-04-14**

###### Global
Fixed the issue related to switching projects in the menu

# **2026-04-14**

###### Editor
Fix bug on video regeneration

# **2026-04-07**

###### Global
Fix minor bugs 

# **2026-03-31**

###### Global
Fix minor bugs 

# **2026-03-30**

###### Editor
Allow 15 seconds video with Kling model

###### Global
Fix minor bugs 

# **2026-03-18**

###### Creation
Add new model Nano banana 2 
Generations that contain errors are clearly marked as such

###### Editor
Added 3 new video models 
Videos can now be added to collections
The resource hub is the default option when you want to add an image in the editor 
Fixed the bug where videos continued to play when switching pages or tools

# **2026-02-25**
Redesigned the reference image section in image creation

# **2026-02-19**

###### Editor
Improvement of generation history by tools and by projects. 

# **2026-02-17**

###### Guide tour
UX / UI improvements on guide tour

###### Creation
Grid view enabled by default
2 images per batch by default

###### Global
Fixed several minor issues affecting app stability.

# **2026-02-11**

###### Global
Access to Seelab is now invitation-only. Free and automatic sign-ups have been discontinued.

# **2026-02-05**

###### Global
Improved resource hub UI/UX and app performance

# **2026**-02-03

###### Global
Introduction of the Resource Hub, enabling centralized access to datasets and resources directly within the application

###### Editor
Improved prompt display and responsiveness

# **2026**-01-27

###### Global
Fixed several minor issues affecting app stability.

# **2026**-01-23

###### Global
New Seelab user interface (visual refresh, no workflow changes)
Light mode / Dark mode available
Overall performance improvements (loading time & responsiveness)

###### Authentication / Home
Redesigned login page
Redesigned homepage for faster access to main features

###### Creation
Grid view available for the creation feed

###### Collections
Batch image download from collections


# **2026**-01-15
###### Global 
* Increase in the number of characters to 3000 in prompts 
###### Creation
* Display of the number of credits used based on the selected model 


# 2025-12-05
###### Editor
* Fixed errors on the first frame for videos from a creation or collection 

# 2025-12-05
###### Collections
* If it is a Nano prediction, retrieve the information from the image preview.
###### Creation
* Fix some issues when clicking the 'Set Model' button close to the images in the batch.
* Fix the number images from the variation to the selected prompt sample number.
###### Editor
* Fix video generation issues and UI adjustments.
###### Global
* Improved error handling for content that violates our policy 

# 2025-12-03
###### Editor
 **🖌️ Complete Redesign of the Editor Interface**
* Introduction of a *liquid-glass* design for menus: modern appearance, subtle transparency, and improved visual hierarchy.
* Enhanced readability and consistency across editor controls.
* Smoother transitions and interactions.

**📐 Reframe System Improvements**
* Overflow is now visible on reframes, making it easier to understand when elements extend beyond their bounds.
* Visual adjustments to improve editing clarity and scene structure comprehension.

**🐞 Bug Fixes & Optimizations**
* Fixed several minor issues affecting editor stability.
* Overall performance and responsiveness improvements.
* Various tweaks to existing features for a smoother user experience.

# 2025-11-03
###### Editor
* Implemented **VOE3 endframe** 
**Settings**
* Added the ability to **delete a project**

# 2025-10-21
###### Model Builder improvements
We’ve fixed several issues related to the rollout of the new Model Builder version.

**Replaced:** *Flux Kontext* with *Nano Banana* for the image reference feature, improving accuracy and consistency of visual results.

# 2025-10-16
**Revamped custom model training flow**
* [**Completely redesigned interface**](https://app.seelab.ai/model-builder) — faster, cleaner, and more flexible.
* **Retrain with improved inputs**, and **transfer models between projects**.
**Video generation**
* [\*\*Video generation cost reduced by 50%](https://app.seelab.ai/pricing/packages):\*\* create twice as many videos for the same budget.
* Drop support of Veo 2 models.

# 2025-10-03
**Video**
VEO 3 now supports both 16:9 and 9:6 resolution with custom durations: 4, 6 or 8 seconds.

**Nano Banana**
Fixed an issue where a user had selected Nano Banana and changed projects.

# 2025-09-25

**New: Google’s Nano Banana arrives in Image Creation 🍌**
Edit any image with precision - *right inside Seelab.*

**How to use:**

1. Add an input image
2. Select the **Nano Banana** tab
3. Ask for the changes you want!

🔒 Available for **Premium** users only.