Hugging Face
Where most open models and weights are published, with model cards that state the licence. Read the card before you ship anything.
Two different jobs share this page. One is finding a model: weights, fine-tunes and LoRAs, usually with sample images so you can judge before downloading. The other is running one without owning a GPU, which is what the API providers sell.
Where most open models and weights are published, with model cards that state the licence. Read the card before you ship anything.
Community host for fine-tunes and LoRAs, with sample images and the prompts that produced them.
Runs open models behind a simple API. Useful for prototyping a pipeline before you commit to hardware.
Inference endpoints tuned for latency, including video models. The usual choice when a workflow needs to feel interactive.
Model hosting and generation in one place, with a browsing experience closer to Civitai than to a cloud console.
Listed in the order we would try them, not by who asked. Prices and free tiers change often — check the vendor's page before you commit. Tool Pantry tools run in your browser and upload nothing.
No. A LoRA is a small adapter applied on top of a base model. It only works with the base it was trained against, which is the most common reason a downloaded LoRA does nothing.
It varies per model and some restrict commercial use or require attribution. The model card states it; the brand name does not.
Local for volume, privacy and iteration. API when you need a specific model your hardware cannot run, or you are still deciding.
We add tools by hand, and only ones we have actually used. Send the link with one sentence on what it does better than the alternatives.