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 notes for 0.4.24

Bowen Xue4b9d43ff04c9
diff --git a/freevideo_engine/release_notes.json b/freevideo_engine/release_notes.json
index 41b3113..4f421f4 100644
--- a/freevideo_engine/release_notes.json
+++ b/freevideo_engine/release_notes.json
@@ -1,21 +1,56 @@
{
"schema": 1,
- "product_version": "0.4.23",
+ "product_version": "0.4.24",
"en": {
- "summary": "Each part planned in the editor can have its own description; low-memory generations explain why they are slower.",
+ "summary": "A person in a source video can be replaced with the character in a person image; reference videos can be used for depth only; the built-in AI sets up a white-model scene from one sentence; an earlier video's prompt and settings can be reused; decoding on cards with less video memory is quicker.",
"changes": [
- "Generation: When a generation runs in low-memory mode, the progress view says why it is slower.",
- "Editor: Each part of a video planned in the editor can now have its own description, and a continued part uses exactly what you write for it. The highlight on characters mentioned with @ in the prompt box updates as soon as a rewritten prompt is filled in."
+ "Studio: \"Replace person\" in the Media section replaces the person in a source video with the character in a person image, and can keep the source video's sound; if that sound cannot be added, the finished video is still kept. A reference video can be set to \"Depth only\"; its depth is computed once and reused by later requests.",
+ "Creation panel: after an earlier video is selected in Recent videos, \"Reuse settings\" fills its prompt, picture size and duration back into the panel; \"Undo\" restores the previous values within 10 seconds.",
+ "White models: when no external Agent is connected, the white-model button in the chat box works with the built-in AI. Describe the shot in one sentence; if a ready-made scene fits, a white model is generated for confirmation, otherwise the reason is shown and the sentence is kept.",
+ "Long videos: when a description is split across parts, the story is no longer repeated in every part; the shared text keeps only what stays the same, such as people, place, lighting and style. Without the prompt model, the description is split across the parts by sentence instead of every part using the whole description, and the creation panel offers to download the prompt model; a download in progress is paused when generation starts.",
+ "Editor: a continued part can be as short as 5 seconds, and on Mac and on computers that cannot make 10 seconds at once a new part starts at 5 seconds; a video with a continued part shorter than 10 seconds has at most 4 parts. A description over the length limit is pointed out before sending, including on a retry.",
+ "Generation: after other ComfyUI workflows have run, the video memory they hold is released before a picture or a prompt rewrite starts, without restarting ComfyUI. A missing text encoder model is detected before encoding starts, with repair guidance; if a model repair fails while downloading, the original file is restored. When generation cannot start because the installation is in use, the failure details name the programs holding it open. When the GPU checks before switching to int8 fail, the failure card lists the reason for each check.",
+ "Memory and speed: on graphics cards that cannot hold the whole decoder, decoding no longer prepares the same layers again for every video segment or every new request while memory allows, with identical output. On most Windows graphics cards with 8 to 12 GB of video memory, the first pass of two-pass videos between 10 and 12 seconds without LoRA computes 8 attention heads at a time instead of 4, as shorter videos already did. On Windows, when other programs free video memory during a generation, the next pass and decoding use the recovered memory.",
+ "Install: setup no longer stops with a dependency mismatch after the installation folder was moved, copied or restored, and a dependency folder too deep for Windows is reported as a long path. Text encoder and tokenizer files deleted after installation are restored from the local copy before encoding and during repair, without downloading.",
+ "Phone access: the phone page works when local network access is switched on in the launcher, and no longer shows \"Connection lost. Reconnecting…\" with no content.",
+ "Agents: the install-skill command installs the FreeVideo skill for an Agent, also from deeply nested Windows folders. The tool list an Agent receives is shorter: common tools are listed in full and the others are opened through a help tool.",
+ "Diagnostic reports: when ComfyUI restarts during a generation, the report of that run is marked as interrupted instead of running, and a long video keeps the report of the part that was interrupted."
]
},
"zh": {
- "summary": "剪辑里规划的每一段可以单独写描述;低显存模式下的生成会说明较慢的原因。",
+ "summary": "可以用人物图中的角色替换源视频里的人物;参考视频可以仅参考深度;内置 AI 可以用一句话搭出白模场景;可以复用之前视频的提示词和设置;显存较小的显卡解码更快。",
"changes": [
- "生成:低显存模式下,进度区会说明这次生成较慢的原因。",
- "剪辑视图:剪辑里规划的每一段现在都可以单独写描述,接着生成的一段会用为它写的描述。改写后的提示词填回时,@人物 高亮立即刷新。"
+ "工作室:“素材”一栏新增“替换人物”,用人物图中的角色替换源视频里的人物,可选保留源视频的声音;声音未能加入时,生成的视频仍会保留。参考视频可以勾选“仅参考深度”,深度只计算一次,之后的请求直接复用。",
+ "创作面板:在“最近作品”中选中之前的视频后,点“复用设置”可以把它的提示词、画面尺寸和时长填回面板;10 秒内点“撤销”可以恢复原来的内容。",
+ "白模:未连接外部 Agent 时,聊天框的白模按钮也可以使用。用一句话描述镜头,有合适的现成场景就先生成白模供确认,没有则说明原因并保留输入。",
+ "长视频:描述分到各段时,不再在每一段重复整个故事,各段共用的部分只保留人物、场景、光线和风格等不变的内容。未安装提示词模型时,描述按句子顺序分到各段,不再每段都用整段描述,创作面板会提示下载提示词模型;开始生成时,正在进行的下载会暂停。",
+ "剪辑视图:接着生成的每段最短可以是 5 秒,在 Mac 和无法一次生成 10 秒的电脑上,新的一段默认 5 秒;含短于 10 秒的接续段时,一个视频最多 4 段。描述超过长度上限时,发送前(包括重试时)就会提示。",
+ "生成:在 ComfyUI 里跑过其他工作流之后,生成图片和改写提示词前会先释放这些工作流占用的显存,无需重启 ComfyUI。文本编码器模型缺失时,会在编码开始前检测并给出修复指引;模型修复在下载中失败时,会还原原来的文件。安装正被占用而无法开始生成时,失败详情会写出占用它的程序。切换到 int8 前的 GPU 检查失败时,错误卡片会列出每项检查的失败原因。",
+ "内存与速度:显存放不下整个解码器的显卡,在内存允许时解码不再为每个视频片段或每次新请求重复准备同样的层,输出不变。显存 8–12 GB 的大多数 Windows 显卡上,10–12 秒、不带 LoRA 的两遍视频,第一遍每次计算的注意力头由 4 个增加到 8 个,与更短的视频相同。Windows 上,生成过程中其他程序释放显存后,下一遍和解码会用上恢复的显存。",
+ "安装:安装目录被移动、复制或还原后,安装不再因依赖不一致而停下;依赖目录层级过深时会按长路径问题提示。安装后被删掉的文本编码器和分词器文件,会在编码前和修复时从本地副本还原,不需要下载。",
+ "手机访问:在启动器里打开局域网访问后,手机页可以正常使用,不再一直显示“连接断了,正在重新连接…”且没有内容。",
+ "Agent:install-skill 命令可以为 Agent 安装 FreeVideo 技能,Windows 上层级很深的目录也能装。Agent 拿到的工具列表更短:常用工具完整列出,其余工具通过帮助工具打开。",
+ "诊断报告:生成过程中 ComfyUI 重启后,这次运行的报告会标为已中断,不再显示为运行中;长视频会保留被中断那一段的报告。"
]
},
"history": [
+ {
+ "product_version": "0.4.23",
+ "en": {
+ "summary": "Each part planned in the editor can have its own description; low-memory generations explain why they are slower.",
+ "changes": [
+ "Generation: When a generation runs in low-memory mode, the progress view says why it is slower.",
+ "Editor: Each part of a video planned in the editor can now have its own description, and a continued part uses exactly what you write for it. The highlight on characters mentioned with @ in the prompt box updates as soon as a rewritten prompt is filled in."
+ ]
+ },
+ "zh": {
+ "summary": "剪辑里规划的每一段可以单独写描述;低显存模式下的生成会说明较慢的原因。",
+ "changes": [
+ "生成:低显存模式下,进度区会说明这次生成较慢的原因。",
+ "剪辑视图:剪辑里规划的每一段现在都可以单独写描述,接着生成的一段会用为它写的描述。改写后的提示词填回时,@人物 高亮立即刷新。"
+ ]
+ }
+ },
{
"product_version": "0.4.22",
"en": {
@@ -206,43 +241,6 @@
"提交问题:反馈里的内存读数分开记录物理可用内存和提交余量。"
]
}
- },
- {
- "product_version": "0.4.15",
- "en": {
- "summary": "Image generation keeps a history of every picture and needs less memory on both small and large graphics cards, error messages everywhere now come with a button to report the problem, and Windows updates download faster in mainland China.",
- "changes": [
- "Image generation: every image generated on this machine is kept in a history, newest first, and can be placed on the canvas, used as a reference, deleted, or opened in its folder. Blank canvases offer Standard and HD sizes.",
- "Image generation: on 6-8 GB graphics cards, decoding uses less graphics memory and runs faster. On cards that can hold the whole model, the weights load straight to the card and no second copy stays in system memory, which cuts memory use after loading from about 15 GB to about 2 GB.",
- "Reporting problems: wherever an error or failure message appears, including generation, editing and export, models and environment, image generation, the agent connection, the library, prompt enhancement, sharing, updates, and the launcher, a Report a problem button next to it opens the feedback form with the context filled in.",
- "AI Autopilot: when a chat cannot be deleted, it now says why and offers Stop and delete; other failures are reported with a button to submit the problem.",
- "White models: only the cat ready-made scene remains, and one click starts it. A white model that was not made now says why and what to do next, and the page shows rendering progress. A question about progress is answered instead of being started as a new request.",
- "Character sheets: in the back view, the head now turns away together with the body.",
- "Mac: long videos can now be generated in parts.",
- "Launcher and updates: Windows updates download faster in mainland China. When GitHub is slow, the launcher can fetch the update from a domestic mirror, and every file from the mirror is checked against the release signature before use. The install confirmation page now fits narrow windows: the sidebar collapses to icons and the buttons stay visible.",
- "Workflows: workflows saved by older versions run again. Options added in later versions that are empty or invalid in an old file are set back to their defaults.",
- "Video generation: the High quality level generates faster. On 8 GB graphics cards, 1920x1088 videos that were refused for falling just short of graphics memory now run. Changing the early steps setting of a video reference now produces a new result instead of reusing the earlier one.",
- "LoRA: a LoRA trained for Wan 2.x now says so when it is selected for the int8 model, instead of only saying it cannot be used.",
- "Linux: on computers with less memory, generating again right after a generation no longer runs out of memory near the end of sampling. On 6 GB graphics cards, Max no longer takes hours to finish."
- ]
- },
- "zh": {
- "summary": "生图工具会保存所有生成过的图片,小显存和大显存的显卡生图都更省内存;所有错误提示旁都有“提交问题”按钮;Windows 版在中国大陆更新更快。",
- "changes": [
- "生图:本机生成过的图片都保存在历史记录里,按时间从新到旧排列,可放到画布、用作参考图、删除或打开所在文件夹。空白画布可选“标准 / 高清”尺寸。",
- "生图:6–8 GB 显存的显卡解码时占用的显存更少,速度更快。显存放得下整个模型的显卡,权重直接加载到显卡,不再在内存里留一份副本,加载后内存占用从约 15 GB 降到约 2 GB。",
- "提交问题:生成、剪辑与导出、环境与模型、生图、智能体连接、作品库、提示词优化、分享、更新和启动器里,出现错误或失败提示的地方旁边都有“提交问题”按钮,点击后带上情况打开问题反馈。",
- "AI 全自动:对话删不掉时会说明原因,并提供“停止并删除”;其他失败也会提示,并带“提交问题”按钮。",
- "白模:现成场景只保留“橘猫跳上书架”,点击直接开始。白模没做成时会说明原因和下一步,渲染中页面显示进度。问白模进度时会回答进度,不再当成新要求。",
- "人物设定图:背面图里头和身体一起转向背后。",
- "Mac:支持分段生成长视频。",
- "启动器与更新:Windows 版在中国大陆更新更快。GitHub 慢时,启动器可以从国内镜像下载更新,镜像上的每个文件都先按发布签名校验。“确认安装”页适配窄窗口:侧栏收成图标,按钮始终可见。",
- "工作流:旧版本存的工作流可以直接运行。旧文件里后加的选项为空或不合法时,改回默认值。",
- "视频生成:“精细”档生成更快。8 GB 显存的显卡上,以前因显存差一点而被拒绝的 1920×1088 视频,现在可以生成。改动视频参考的前期步数设置后,会生成新的结果,不再沿用之前的结果。",
- "LoRA:为 Wan 2.x 训练的 LoRA 选进 int8 模型时,会说明这是给 Wan 2.x 训练的 LoRA,不再只说无法使用。",
- "Linux:内存较小的电脑接着再生成一次时,不再在采样快结束时内存不足。6 GB 显存的显卡选“极致”时,不再要等好几个小时。"
- ]
- }
}
]
}