Skip to content

FreeVideo 0.4.29 - #620

Merged
KBRASK merged 20 commits into
mainfrom
release/0.4.29-public
Nov 2, 2026
Merged

KBRASK merged 20 commits into
mainfrom
release/0.4.29-public

Conversation

@KBRASK

@KBRASK KBRASK commented Nov 2, 2026

Copy link
Copy Markdown
Collaborator

0.4.29: Music can be generated on the second audio track from the generation bar (not on Mac), scenes can be added to the character library, long videos can be extended by typing a length in seconds, and Autopilot chat continues a failed or stopped video from where it left off.

  • Editor: music can be made from the generation bar by dragging a range on the second audio track, which new edits now show by default. Choose a style and a mood and optionally describe the music; if the music model is not installed yet, it is downloaded first. A selected generated piece can be regenerated in place, and one undo restores the previous piece. Generated music is lowered while someone speaks; this can be turned off with Lower during speech in the clip properties. Not available on Mac.
  • Editor: the timeline scrolls vertically when the second audio track, text or subtitle rows do not fit, with the ruler kept in place.
  • Character library: scenes can be added from your own pictures or from several AI candidates, and mentioned with @ in the prompt; the time of day, weather, light and tone written in the prompt are kept in the generated video.
  • Long videos: when an ungenerated draft part or a range on the picture track is selected, the generation bar shows a Duration field in whole seconds. It follows the same rules as dragging the right edge (whole seconds, at least 10 s per part, up to 8 parts); a value out of range is clamped with a short note, and one undo restores the previous length.
  • Long videos: joining parts no longer fails at the last step when one part differs from the first in size or encoding; such a part is now matched to the first part before the parts are joined. When that is not possible, the message names the part and the property that differs.
  • Long videos: a video that already has the most parts a continuous shot can have now says so as soon as it is chosen to be extended, and the limit is checked before generation starts.
  • Long videos: the last continuation part, including a single added part, can be as short as 2 s; parts in the middle still last at least 5 s.
  • Autopilot: Continue generating on a failed or stopped video picks up the same request and keeps the parts already made, also when the Agent is offline. A failed picture is submitted again with the original request. The latest message can be edited and sent again; unfinished tasks after it are stopped first.
  • Agent: when the Connect an agent card cannot get an address, it explains the reason, for example when the page was opened from another device or by machine name; the feedback report includes the status code and error code.
  • Prompt enhancement: when the Agent is asked to improve the prompt before generating, the generation uses the improved text exactly, and is no longer treated as a different prompt because quotation marks were changed while the text was copied.
  • Prompts: asking for no background music in the scene text now works when the prompt still has the starter prompt's music section: the unchanged starter score is replaced with N/A, and a rewritten prompt ends with N/A. A music section written by the user is kept.
  • Speed: the background compile also prepares portrait videos and videos with a reference picture, so their first request no longer compiles GPU programs at the first step of each pass. The one-time background compile takes about 80 seconds longer; results are unchanged.
  • Install: a damaged offline package is now reported by name with a request to download it again, instead of a raw decompression error.
  • Install: downloads over an unstable connection now continue from the part already downloaded instead of stopping after the first round.
  • Install: on Windows, setup now waits and creates the Python environment again when another program, such as security software, holds its Python file open, instead of failing at the first attempt.
  • Install: when Windows refuses to run FreeVideo's Python file, the failure message now says so in any system language and points to the security software.
  • Updates: a downloaded source update is verified against the release signature again every time the launcher starts, not only when it is downloaded.
  • Diagnostics: the diagnostic log times the video worker's start-up steps.

KBRASK added 20 commits November 2, 2026 17:38
…on from its finished parts...

Chat: a failed card runs its own request again, a stopped video goes on from its finished parts, and the newest message can be edited
Agent: generate from an enhanced prompt by reference; eval compares the retyped prompt with typography levelled
…d name the differing field...

Join chain parts of a different size by conforming them to part 1, and name the differing field when that is impossible
…is chosen, and check it...

Say why a video with the most parts cannot be extended as soon as it is chosen, and check it before generation
@KBRASK
KBRASK merged commit a05770f into main Nov 2, 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