Skip to content

Optional image generation models, and install and launcher fixes (0.4.2) - #234

Merged
KBRASK merged 10 commits into
mainfrom
release/0.4.2-public
Oct 14, 2026
Merged

KBRASK merged 10 commits into
mainfrom
release/0.4.2-public

Conversation

@KBRASK

@KBRASK KBRASK commented Oct 14, 2026

Copy link
Copy Markdown
Collaborator

0.4.2: Adds optional image generation models: generate and edit pictures, make several views for character cards, and let the agent use them. Also fixes several install and launcher issues.

  • Adds optional image generation models. "Generate with AI" in the media panel makes a picture from one sentence on a blank canvas, and "Edit this" in the image editor changes the current picture, with up to two more pictures from your media as references.
  • With the image generation models installed, character cards start from a front view and use it as the reference for three-quarter, side, back and close-up views; scene cards are made the same way.
  • The agent can generate or edit pictures and add them to your media, and can first make a frame with people placed as described, then generate the video from it.
  • Setup can install the image generation models at the same time (about 16 GB), and existing installs can download them in the background from the launcher; the download pauses while a video is generating.
  • Online installs into a folder the system code page cannot spell, such as a Chinese folder on an English system, no longer fail at the kernel check.
  • On Linux, when the system compiler is newer than the installed GPU toolkit supports, setup now uses a compatible compiler instead of stopping while building the GPU attention component.
  • When a Windows security feature blocks files FreeVideo needs, the error card now says so and notes that the setting may need to be changed in Windows.
  • After a launcher error, an address or path being typed in the settings is no longer reset to its previous value.
  • When the agent makes a film, a shot that continues the previous one is at least 10 seconds long, 10 seconds by default; a length this computer cannot make in one run is reported before generation starts.
  • In AI Autopilot, the conversation list updates as soon as a job starts or stops, and switching conversations quickly stays on the one selected.

KBRASK added 10 commits October 14, 2026 00:48
…conds long

- 10 seconds by default when no length is given
- A length this computer cannot make in one run is reported before generation starts
…s too new for the GPU toolkit

- An older versioned compiler already installed is used first
- Otherwise a hash-verified portable GCC is downloaded once into FreeVideo's own folder
- Systems whose compiler is supported are unchanged
…first pass

- Later steps and the second pass run without that video
- Requests without the field are unchanged
- The card says what was blocked and that the setting may need to be changed in Windows
- The address, install location, engine folder and Python path apply on Enter or when leaving the field
…rom a short entry

- The kernel check no longer fails on the path
…ent use

- Generate from one sentence on a blank canvas, or edit the current picture with up to two more references
- Character cards start from a front view and use it as the reference for the other views
 scene cards use the image models too
- The agent can generate or edit pictures, and can make a first frame before generating a video
- Setup can install the models, and existing installs can download them in the background
@KBRASK
KBRASK merged commit e73146e into main Oct 14, 2026
5 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant