Skip to content

Make videos on the computer you already own. FreeVideo runs MiniMax H3 in as little as 8 GB of VRAM and 16 GB of RAM, and adapts its acceleration path to your hardware.

Release 0.4.10

Bowen Xuef8a2da8ae3eb
diff --git a/freevideo_engine/release_notes.json b/freevideo_engine/release_notes.json
index add3d22..743394c 100644
--- a/freevideo_engine/release_notes.json
+++ b/freevideo_engine/release_notes.json
@@ -1,41 +1,72 @@
{
"schema": 1,
- "product_version": "0.4.9",
+ "product_version": "0.4.10",
"en": {
- "summary": "Quality levels are reworked: Medium is one pass of 8 steps, and High and Max use step caches to finish much sooner; decoding on Windows reads ahead earlier on slow drives, and the editor handles ranges, splits and text tracks more reliably.",
+ "summary": "High on Mac uses the step cache and finishes much sooner; in the editor, audio clips can move to another audio track, and several notices and narrow-window layouts are clearer; workflows saved by an earlier version generate again.",
"changes": [
- "Quality levels: Medium is one pass of 8 steps; High and Max run 20 steps with step caches and finish much sooner than plain 20 steps.",
- "Decoding on Windows: read-ahead is sized by physical memory and starts earlier on slow drives, so the end of a run waits less for the disk.",
- "When Windows runs out of virtual memory, in any system language, FreeVideo now retries the generation automatically in a fresh process and reports a memory shortage if it still fails.",
- "The progress estimate counts reference images, so requests with reference images show a closer total time from the start.",
- "Editor: dragging a range's left edge to the start of the timeline no longer pushes its right edge later; splitting a sped-up or reversed part keeps the fade-in only on the first half and the fade-out only on the second.",
- "Editor: drag-selecting parts is smooth again on timelines with many parts.",
- "Editor text: clicking the side Content box right after pressing T keeps the new text track, and dropping text onto a locked text track says the track is locked.",
- "Long videos: each part's description can also be edited in a larger window.",
- "Chat: when a conversation is full, the notice appears once under the message and its button starts a new chat instead of retrying.",
- "Export: the sizes offered in the export dialog are rounded the same way as the saved work.",
- "Diagnostic reports record how much of the graphics card other programs were using during each sampling step.",
- "Launcher: when the browser cannot be opened automatically, the message says to click Copy address and open it in a browser, in Chinese as well. Canvas margin labels stay readable and aligned. Nodes: width, height, duration and seed have Chinese labels."
+ "Mac: High uses the step cache on the first pass and finishes much sooner, and the starting time estimate is based on the chip, so it is closer from the first step.",
+ "Editor: an audio clip dragged from the library onto the second audio track lands there, and a single audio clip on the timeline can be dragged to another audio track.",
+ "Editor: pressing split or trim while the playhead is outside the selected part, or asking for full screen where the browser refuses it, now says why in one line.",
+ "Character mentions written back to back, with no space between the names, are each recognised, and the character list opens again right after a name.",
+ "Autopilot: while a task is running, the Autopilot button in the header stays whole and clickable in narrow windows.",
+ "Chat: on phones and other narrow windows, button names quoted in notices stay on one line.",
+ "Diagnostic reports for failed image and video requests record the available memory when the request started and when the generation process ended, and whether the system appears to have ended the process.",
+ "Nodes: the English Width, Height and Seed labels are capitalised like the other fields.",
+ "Generating from a workflow saved by an earlier version, or from a restored tab, no longer fails with an invalid step cache setting."
]
},
"zh": {
- "summary": "质量档位调整:标准为单遍 8 步,精细和极致用步间缓存,快得多;Windows 解码在慢硬盘上更早预读;编辑器的区间、切分和文字轨更可靠。",
+ "summary": "Mac 精细档使用步间缓存,快得多;编辑器里音频片段可以拖到另一条音频轨;几处提示和窄窗口布局更清楚;旧版本保存的工作流又能正常生成。",
"changes": [
- "质量档位:标准为单遍 8 步;精细和极致为 20 步加步间缓存,比纯 20 步快得多。",
- "Windows 解码:预读按物理内存决定大小,并在慢硬盘上更早开始,生成收尾时等硬盘的时间更短。",
- "Windows 虚拟内存耗尽时,不论系统语言,FreeVideo 现在会在新进程中自动重试生成,仍失败时提示内存不足。",
- "进度估计把参考图计入,带参考图的请求一开始就显示更接近实际的总时间。",
- "编辑器:把区间左边拖到时间线开头,右边不再被往后推;切分加速或倒放的片段时,淡入只留在前半段,淡出只留在后半段。",
- "编辑器:片段很多时,框选重新变得流畅。",
- "编辑器文字:按 T 后马上点侧边“内容”框,新文字轨会保留;把文字拖到已锁定的文字轨上会提示该轨已锁定。",
- "长视频:每段描述也能在放大窗口里编辑。",
- "对话:对话已满时,提示只在消息下出现一次,按钮换成“新对话”。",
- "导出:导出窗口里给出的尺寸和保存的作品用同样的方式取整。",
- "诊断报告记录每一步采样时其他程序占用显卡的比例。",
- "启动器:浏览器没能自动打开时,提示点“复制地址”到浏览器里打开,中文界面也显示中文。画布边距标签更清楚、对齐。节点:宽度、高度、时长和种子有中文标签。"
+ "Mac:精细档第一遍使用步间缓存,快得多;开始时的预计时间按芯片给出,从第一步起就更接近实际。",
+ "编辑器:从素材库把音频拖到第二条音频轨会放在该轨;时间线上单个音频片段可以拖到另一条音频轨。",
+ "编辑器:播放头不在所选片段上时按切分或修剪,或在浏览器不允许全屏的地方点全屏,会用一行字说明原因。",
+ "连着写、名字之间没有空格的角色提及都能被识别,写完一个名字后接着输入也会弹出角色列表。",
+ "AI 全自动:有任务在跑时,窄窗口里顶栏的“AI 全自动”按钮也始终完整可点。",
+ "对话:手机等窄窗口里,提示中引号内的按钮名不再被拆到两行。",
+ "图像和视频失败请求的诊断报告现在记录请求开始和生成进程结束时的可用内存,并标明进程是否疑似被系统结束。",
+ "节点:英文界面里 Width、Height、Seed 的大小写与其他项一致。",
+ "修复:用旧版本保存的工作流或恢复的标签页生成时提示步间缓存参数无效。"
]
},
"history": [
+ {
+ "product_version": "0.4.9",
+ "en": {
+ "summary": "Quality levels are reworked: Medium is one pass of 8 steps, and High and Max use step caches to finish much sooner; decoding on Windows reads ahead earlier on slow drives, and the editor handles ranges, splits and text tracks more reliably.",
+ "changes": [
+ "Quality levels: Medium is one pass of 8 steps; High and Max run 20 steps with step caches and finish much sooner than plain 20 steps.",
+ "Decoding on Windows: read-ahead is sized by physical memory and starts earlier on slow drives, so the end of a run waits less for the disk.",
+ "When Windows runs out of virtual memory, in any system language, FreeVideo now retries the generation automatically in a fresh process and reports a memory shortage if it still fails.",
+ "The progress estimate counts reference images, so requests with reference images show a closer total time from the start.",
+ "Editor: dragging a range's left edge to the start of the timeline no longer pushes its right edge later; splitting a sped-up or reversed part keeps the fade-in only on the first half and the fade-out only on the second.",
+ "Editor: drag-selecting parts is smooth again on timelines with many parts.",
+ "Editor text: clicking the side Content box right after pressing T keeps the new text track, and dropping text onto a locked text track says the track is locked.",
+ "Long videos: each part's description can also be edited in a larger window.",
+ "Chat: when a conversation is full, the notice appears once under the message and its button starts a new chat instead of retrying.",
+ "Export: the sizes offered in the export dialog are rounded the same way as the saved work.",
+ "Diagnostic reports record how much of the graphics card other programs were using during each sampling step.",
+ "Launcher: when the browser cannot be opened automatically, the message says to click Copy address and open it in a browser, in Chinese as well. Canvas margin labels stay readable and aligned. Nodes: width, height, duration and seed have Chinese labels."
+ ]
+ },
+ "zh": {
+ "summary": "质量档位调整:标准为单遍 8 步,精细和极致用步间缓存,快得多;Windows 解码在慢硬盘上更早预读;编辑器的区间、切分和文字轨更可靠。",
+ "changes": [
+ "质量档位:标准为单遍 8 步;精细和极致为 20 步加步间缓存,比纯 20 步快得多。",
+ "Windows 解码:预读按物理内存决定大小,并在慢硬盘上更早开始,生成收尾时等硬盘的时间更短。",
+ "Windows 虚拟内存耗尽时,不论系统语言,FreeVideo 现在会在新进程中自动重试生成,仍失败时提示内存不足。",
+ "进度估计把参考图计入,带参考图的请求一开始就显示更接近实际的总时间。",
+ "编辑器:把区间左边拖到时间线开头,右边不再被往后推;切分加速或倒放的片段时,淡入只留在前半段,淡出只留在后半段。",
+ "编辑器:片段很多时,框选重新变得流畅。",
+ "编辑器文字:按 T 后马上点侧边“内容”框,新文字轨会保留;把文字拖到已锁定的文字轨上会提示该轨已锁定。",
+ "长视频:每段描述也能在放大窗口里编辑。",
+ "对话:对话已满时,提示只在消息下出现一次,按钮换成“新对话”。",
+ "导出:导出窗口里给出的尺寸和保存的作品用同样的方式取整。",
+ "诊断报告记录每一步采样时其他程序占用显卡的比例。",
+ "启动器:浏览器没能自动打开时,提示点“复制地址”到浏览器里打开,中文界面也显示中文。画布边距标签更清楚、对齐。节点:宽度、高度、时长和种子有中文标签。"
+ ]
+ }
+ },
{
"product_version": "0.4.8",
"en": {
@@ -173,64 +204,6 @@
"浏览器翻译页面时不再翻译产品名。"
]
}
- },
- {
- "product_version": "0.4.4",
- "en": {
- "summary": "Continuing a video segment by segment no longer stops with a memory error, medium-size videos on Windows with 16 GB or smaller cards are fast again in the second pass, and image generation on Windows no longer stalls. The editing view gains reference pictures and imported-video continuation, and several issues that stopped generation or setup are fixed.",
- "changes": [
- "Continuing a video segment by segment no longer stops with a memory error from the second segment on.",
- "Windows: medium-size videos on graphics cards with 16 GB or less no longer slow down in the second pass.",
- "Image generation: on Windows it no longer stalls while the image model starts, reports a false out-of-memory error after loading, or stalls while checking downloaded model files; tall pictures no longer show purple vertical lines or a grid texture.",
- "After a video finishes, FreeVideo releases graphics and system memory right away unless the next part is about to start, and gives way at once to image generation or other programs.",
- "Editing view: the generation bar takes reference pictures (upload one or make one with the image model, then set it as reference, first frame or last frame), every Generate press answers at once, and queued parts stay queued after the page is reloaded and start by themselves; if generation cannot run, they go back to drafts with the reason.",
- "Editing view: videos imported from your computer can be extended and continued, files dropped on the timeline land where they are dropped, reopening it from the launcher keeps it usable, and keys pressed in the media library no longer change the timeline.",
- "Mac: generating with reference pictures no longer runs out of memory while encoding; the compatibility setting, which only applies to separate graphics cards, is no longer shown.",
- "Additional model folders entered in the node settings are now saved and used when FreeVideo looks for models and starts.",
- "Edge model files now download from the ModelScope domestic site, and the image model gains an additional mirror source.",
- "Image editor: leaving or reloading the page with unsaved changes now asks first. Flipping, resetting, fitting or dragging the locked original works on an automatic copy as one undo step. Renaming a layer by double-click keeps the name, and invalid canvas sizes are explained instead of failing silently.",
- "Small mismatches no longer stop the launcher, setup, saved Agent films and cast cards, subtitle import, the image editor, sharing or prompt enhancement; FreeVideo continues and repairs what it can. Turning off or cancelling prompt enhancement while it runs stops it cleanly, and the release link in the update notice opens the latest release.",
- "A workflow restored with an empty Total frames value no longer fails with a frame-count error; it generates by duration."
- ]
- },
- "zh": {
- "summary": "一段接一段连续生成不再因内存报错;Windows 上 16 GB 及以下显卡生成中等尺寸视频,第二遍恢复原来的速度;Windows 图像生成不再卡住。剪辑视图可以加参考图、接续导入的视频,另修复了几处会让生成或安装中断的问题。",
- "changes": [
- "一段接一段连续生成时,从第二段起不再因内存不足报错。",
- "Windows:16 GB 及以下显卡生成中等尺寸视频时,第二遍不再变慢。",
- "图像生成:Windows 上图像模型启动时不再卡住、加载完不再误报内存不足,下载后校验文件不再卡住;高图上不再出现紫色竖线和网格纹。",
- "视频生成完会立即释放显存和内存;下一段马上开始时才短暂保留,遇到图像生成或其他程序要用时立刻让出。",
- "剪辑视图:生成条可以加参考图(上传图片或用图像模型生成一张,可设为参考、首帧或尾帧);每次点“生成”都会立刻有反应,排队的段刷新页面后仍在排队、轮到时自动开始,不能生成时退回草稿并说明原因。",
- "剪辑视图:从电脑导入的视频也能往后接续生成,拖到时间线上的文件落在松手的位置;从启动入口再次进入时可以正常操作,素材库里按键不再改动时间线。",
- "Mac:用参考图生成时,编码阶段不再报内存不足;只对独立显卡起作用的兼容性设置不再显示。",
- "节点设置里填写的“其他模型目录”现在会保存,查找模型和启动时都会用到。",
- "Edge 模型文件改从魔搭国内站下载,图像模型增加一个镜像下载源。",
- "图片编辑器:有未保存的改动时离开或刷新页面会先提示;对已锁定的原图翻转、重置、适配或拖动时,自动在副本上操作并算一步撤销;双击重命名图层保留名称;画布尺寸不合法时给出提示而不是无反应。",
- "启动器、安装、Agent 已存的影片和角色卡、字幕导入、图片编辑器、分享和提示词改写遇到小偏差不再中断,FreeVideo 会继续并自动修复能修的部分;提示词增强运行中关闭或取消时会正常停止,更新提示里的发布页链接打开最新版本。",
- "恢复的工作流把“总帧数”留空时,生成不再因帧数校验报错,按时长正常生成。"
- ]
- }
- },
- {
- "product_version": "0.4.3",
- "en": {
- "summary": "LAN access settings of offline-package installations are kept when the launcher is reopened, and the agent no longer replies after a job is stopped on the page. Also includes several fixes; the image generation models can now be downloaded and installed normally.",
- "changes": [
- "With an offline-package installation, LAN access and its port now stay as set after the launcher is reopened.",
- "After a job is stopped on the page, the agent adds no message about it and does not retry on its own.",
- "When the agent asks for a video length this computer cannot make, it now gets a clear explanation instead of an error.",
- "The image generation models can now be downloaded and installed normally."
- ]
- },
- "zh": {
- "summary": "用离线包安装时,局域网访问的设置在重开启动器后保留;在页面上停止任务后,Agent 不再另外回复;另有几处修复,图像生成模型现在可以正常下载和安装。",
- "changes": [
- "用离线包安装时,局域网访问的开关和端口在重开启动器后保持不变。",
- "在页面上停止任务后,Agent 不再另外回复,也不会自行重试。",
- "Agent 请求的视频长度超出这台电脑能做的范围时,会收到明确的说明,不再出错。",
- "图像生成模型现在可以正常下载和安装。"
- ]
- }
}
]
}