Model
Trends
.ai
Model
Trends
.ai
die besten Open-Source-KI-Modelle

So installierst du Wan2GP

Video generation for the GPU poor: Wan, Hunyuan, LTX and more on 6 to 12 GB cards with a simple web interface.
Videogenerierung
Windows
Linux
Lizenz: Apache-2.0

Was ist Wan2GP?

Wan2GP (Wan for the GPU Poor) by deepbeepmeep is a free, open source app that runs the big open source video models, Wan 2.x, Hunyuan Video, LTX Video, FramePack-style generators and image models like Flux and Qwen Image, on ordinary consumer graphics cards. It does this with aggressive memory management and quantization, so a 12 GB card can generate clips that normally need 24 GB or more. The Gradio interface is a straightforward form: prompt, settings, generate.
Wan2GP is for anyone who wants local AI video without building ComfyUI graphs and without a top-end GPU. It is Windows and Linux only and expects you to be comfortable with a small amount of command line work (or to use Pinokio, which installs it in one click).
AD
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).

Was du brauchst

Windows 10 or 11 or Linux with an NVIDIA GPU: 6 GB VRAM for the smallest models, 12 GB for comfortable Wan 2.x work, 16 to 24 GB for high resolution and longer clips. 32 GB of system RAM is strongly recommended, since models are swapped to RAM. 50 GB or more of disk space for model downloads.

So bekommst und installierst du Wan2GP

  1. Easiest: install Pinokio and pick Wan2GP from its Discover page; it installs everything with one click.
  2. Manual: install Python 3.10 and Git, clone the GitHub repository, create a virtual environment and install PyTorch with CUDA (the README gives the exact commands).
  3. Run pip install -r requirements.txt in the virtual environment. Optional speed-ups like SageAttention are explained in the README.
  4. Start it with python wgp.py. The browser opens on the Gradio page; the model you pick is downloaded automatically from Hugging Face on first use.
  5. Add --profile to choose a memory profile for your card, or pick it in the interface configuration tab afterwards.
Lade nur über die offiziellen Links auf dieser Seite herunter. Installer von anderswo können veraltet oder manipuliert sein. ModelTrends.ai hostet keine Dateien.
AD
PirateDiffusion
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.

So benutzt du Wan2GP

  1. Choose a model at the top: Wan 2.x text to video, image to video, Hunyuan Video, LTX Video, or an image model such as Flux or Qwen Image.
  2. Write your prompt (and a negative prompt), set the resolution, number of frames and steps. Start small: 480p, 49 frames, 20 to 30 steps.
  3. For image to video, upload a start image; the model animates it following the prompt.
  4. Add LoRAs from the LoRA section (put the files in the loras folder for your model type) and set their multipliers; include the trigger words from the model page.
  5. Press Generate and watch the progress; clips are saved in the outputs folder and shown in the gallery when done. Queue several prompts and let them run.

Tipps und häufige Probleme

  • Choose a lower memory profile if you get out of memory errors; profile 4 or 5 trades speed for lower VRAM.
  • Distilled or step-accelerated LoRAs (CausVid, LightX2V, FusionX) cut generation to 4 to 8 steps and are the biggest speed win on small cards.
  • TeaCache and Skip Layer Guidance options speed things up with little quality loss; try them once your settings work.
  • Keep the project updated with git pull; new models arrive almost weekly.

Modelle, die du in Wan2GP ausführen kannst

Wan2GP runs the Wan, Hunyuan and LTX video models in this catalog and their LoRAs, plus Flux and Qwen Image for still pictures.
AD
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.

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.
Windows
Mac
Linux
So installierst du Stable Diffusion WebUI (AUTOMATIC1111)
The classic Stable Diffusion web interface: tabs, sliders and thousands of extensions. The app most tutorials were written for.
Windows
Mac
Linux
So installierst du Stable Diffusion WebUI Forge
The faster, lighter fork of the AUTOMATIC1111 interface with Flux support. Same tabs, much less VRAM.
Windows
Linux
So installierst du Fooocus
Type a prompt, get a great SDXL image. Fooocus hides the settings and does the prompt engineering for you.
Windows
Mac
Linux
So installierst du SD.Next
A heavily modernized fork of the original WebUI that runs Stable Diffusion, SDXL, Flux, Qwen, Chroma and dozens of other model families on NVIDIA, AMD, Intel and Apple hardware.
Windows
Mac
Linux
So installierst du Invoke (InvokeAI)
A polished creative studio with an infinite canvas, layers and inpainting, built for artists rather than engineers.
Windows
Mac
Linux
So installierst du SwarmUI
A friendly, modern interface on top of a ComfyUI engine: simple generate tab for everyone, full node graph when you want it.
Windows
Mac
Linux
So installierst du Draw Things
The best native app for Mac, iPhone and iPad: Stable Diffusion, Flux, Wan video and more with no setup and no terminal.
Mac
iPhone
iPad
So installierst du DiffusionBee
The one-click Stable Diffusion app for Mac: download, open, type, done. A Windows version exists too.
Mac
Windows
So installierst du Stability Matrix
One launcher that installs and updates ComfyUI, Forge, A1111, Fooocus, SwarmUI and more, and shares your models between them.
Windows
Mac
Linux
So installierst du Pinokio
A browser for AI apps: one-click installs for ComfyUI, Forge, Wan2GP, FramePack, voice and music tools, each in its own isolated environment.
Windows
Mac
Linux
So installierst du Krita AI Diffusion
Generative AI inside the free Krita painting program: paint, mask and generate on layers with live preview.
Windows
Mac
Linux
So installierst du Amuse
A simple Windows app for AMD and other PCs that generates images with no Python and no command line.
Windows
So installierst du Easy Diffusion
A one-click installer and simple web interface for Stable Diffusion that just works on Windows, Mac and Linux.
Windows
Mac
Linux
So installierst du FramePack
Generate long videos frame by frame on a 6 GB laptop GPU, with progressive preview as it renders.
Windows
Linux
So installierst du LM Studio
Run open text models like Llama, Qwen, Gemma and Mistral on your Mac or PC with a chat window and a local API.
Windows
Mac
Linux
So installierst du Ollama
The developer favourite for local LLMs: one command downloads and runs Llama, Qwen, Gemma, DeepSeek and more, with a built-in API.
Windows
Mac
Linux