Alex "mcmonkey" Goodwin

Ah, you're on an AMD GPU? See here https://github.com/Stability-AI/StableSwarmUI/issues/23 tldr: AMD GPUs are a pain to get working properly, but it can be done with a bit of manual forcing...

That's certainly one way to workaround that. Ideally the root issue should just be fixed - ie gradio should be made to properly close the port somehow. The weird thing...

@tensiondriven it was already fixed actually! Gradio 3.28 has the fix, thanks to https://github.com/gradio-app/gradio/pull/3959

Can be detected via the `edm_vpred` keys. CosXL should work as-is with just the specific Cos-V-EDM schedule applied, Edit should be able to work via the existing ip2p support. You...

Have you followed the install steps for monkeypatch listed on the wiki @ https://github.com/oobabooga/text-generation-webui/wiki/GPTQ-models-(4-bit-mode)#using-loras-in-4-bit-mode ?

The problem is `monkeypatch` breaks things - it would probably need a separate install option for which you want (monkeypatch or normal). At least until more things get merged upstream.

@bgagandeep Have you followed the install steps for monkeypatch listed on the wiki @ https://github.com/oobabooga/text-generation-webui/wiki/GPTQ-models-(4-bit-mode)#using-loras-in-4-bit-mode ?

As noted in that thread, adding `Question: ` and `User: ` may improve quality of results on the Alpha. (It's still not going to be great, but a little better)

lol, docs got moved around a bit since then -- current link is https://github.com/oobabooga/text-generation-webui/blob/main/docs/05%20-%20Training%20Tab.md

Should prioritize finding out exactly what the remote code execution is and replacing it with something safe.