ai newsMi., 4. Nov.
EilmeldungGoogle’s first Suncatcher satellite runs an AI workload in orbit

Why my 15 GB AI model download kept failing near the end

Background Once ComfyUI was installed, the real hurdle was the models. One image-to-video template needs six files, one of them 20 GB and another 15 GB. ComfyUI in the browser has a Download button, but there were three problems: Files land in the Downloads folder, not ComfyUI's models folder, so y

dev.toMittwoch 04:42 · 04.11.2 Min. Lesezeit

Posted on Nov 4 • Originally published at amsyn.org

Once ComfyUI was installed, the real hurdle was the models. One image-to-video template needs six files, one of them 20 GB and another 15 GB. ComfyUI in the browser has a Download button, but there were three problems:

Every ComfyUI workflow lists the models it needs, each with a file name and a folder (for example vae or text_encoders). The helper reads that list from the built-in templates and saved workflows, looks at Downloads every 5 seconds, and moves a file when its name matches exactly and its size has stopped changing. Anything it doesn't recognise is left alone, and it never overwrites or deletes.

for name in listdir ( downloads ): # every 5 s: move finished downloads a workflow lists folder = index. get ( name ) # e.g. "vae", learned from workflow JSON if folder and size_is_stable ( name ): # partial downloads have temporary names anyway move ( name, models / folder / name ) Enter fullscreen mode Exit fullscreen mode Each look at the folder is so quick that the helper barely uses any CPU.

Save the workflow in ComfyUI with Control and S, choose option 8 in the tool and pick the workflow by number. No model names to type. It lists the missing files, their sizes, where they go and whether there's enough disk space, then downloads them one by one with a progress bar. Close the window, lose the connection or shut down, and choosing it again continues from where it stopped.

Most models live on Hugging Face and need a token. The first install step asks for a Fine-grained, Read-Only token, checks straight away which account it belongs to, and warns if it can also write. The token is saved where Hugging Face's own tools look for it, never in an environment variable or a log.

The 15 GB model that kept failing in the browser now finishes in one go. If the computer shuts down halfway, the download continues where it stopped instead of starting from zero. Each model goes straight into the right folder rather than sitting in Downloads, and a model that needs a licence is listed at the end with its page opened for you, instead of a confusing error.

Cover: Container ship arriving port by Unknown, CC0 1.0.

Quelle: dev.to (dev.to). Original öffnen