FramePack by lllyasviel is a free, open source video generation program built on a technique that compresses past frames so the memory needed stays constant however long the video gets. In practice it makes 60 second clips on a 6 GB GPU, showing you the video as it grows. It ships as a small Gradio app with a one-click Windows package and uses a Hunyuan Video based model, with an image as the starting point.

FramePack is for anyone with a modest NVIDIA card who wants to animate a picture into a long clip without a workstation. It is simpler and more focused than Wan2GP, which supports many more models.

Keine Installation nötig – KI-Modelle in der Cloud ausführen

BitVector Prism ist der einfachste Einstieg: Modell wählen, Prompt eingeben und in einer übersichtlichen Web-App generieren, ohne etwas einzurichten. BitVector gibt es auch auf Discord und im Web (SpyGlass).

BitVector ausprobieren

Was du brauchst

Windows or Linux with an NVIDIA RTX 30, 40 or 50 series GPU with at least 6 GB VRAM (fp16 and bf16 support required). 32 GB of system RAM recommended. About 30 GB of disk space for the models, which are downloaded on first run.

So bekommst und installierst du FramePack

Windows: download the one-click package linked on the GitHub page, extract it and run update.bat once, then run.bat.
Linux or manual: install Python 3.10, clone the repository, install PyTorch with CUDA and run pip install -r requirements.txt, then python demo_gradio.py.
Pinokio also offers FramePack as a one-click install.
On first start the models (over 30 GB) download from Hugging Face; the interface opens in the browser when they are ready.

Lade nur über die offiziellen Links auf dieser Seite herunter. Installer von anderswo können veraltet oder manipuliert sein. ModelTrends.ai hostet keine Dateien.

Keine Installation nötig – KI-Modelle in der Cloud ausführen

PirateDiffusion gibt es nur auf Telegram und richtet sich an Profis: tausende Modelle, LoRAs und Workflows per Chat-Befehl, mit unbegrenzter Generierung zum Festpreis.

PirateDiffusion ausprobieren

So benutzt du FramePack

Upload a start image: the first frame of your video. Portraits and clear subjects work best.
Write a short prompt describing the motion, for example "the woman turns and smiles, wind in her hair".
Set the total video length in seconds and the steps (25 is the default). Leave the other settings until you know how your card behaves.
Press Start Generation. The video appears and extends in sections while it renders; you can stop early and keep what is done.
Finished clips are saved in the outputs folder as MP4. Try the TeaCache option for faster renders once you have a result you like.

Tipps und häufige Probleme

The GPU Memory Preservation slider trades speed for safety; raise it if you get out of memory errors.
Short, concrete motion prompts work better than long descriptive scene prompts; the image already defines the scene.
The F1 variant (demo_gradio_f1.py) generates forward in time and gives more dynamic motion.
Expect a few minutes per second of video on a laptop GPU; keep test renders short.

Modelle, die du in FramePack ausführen kannst

FramePack uses its own Hunyuan Video based model, which it downloads itself. Hunyuan LoRAs from this catalog can be loaded by community forks such as FramePack Studio.

Hunyuan-Modelle

Keine Installation nötig – KI-Modelle in der Cloud ausführen

Keine GPU, keine Downloads, kein Python. Diese Dienste führen dieselben Open-Source-Modelle auf ihren eigenen Servern aus, sodass du in einer Minute im Browser, auf Discord oder Telegram loslegen kannst.

BitVector ausprobieren

PirateDiffusion ausprobieren

Links

Diese Links führen zu den Seiten der Hersteller. ModelTrends.ai ist nicht mit ihnen verbunden und hostet keine Software.

Weitere lokale Apps

So installierst du ComfyUI

The node-based powerhouse for Stable Diffusion, Flux, Wan video and almost every new open source model. Free, open source, for Windows, Mac and Linux.