Ankur Kaul
Ankur Kaul
SSD-1B is a quantized version of SDXL where the precision on the weights are reduced from higher precision float point 16 / 32 to 1 Bit weights. This makes the...
if you run app.py it downloads all the file in huggingface hub cache or manually download them and place them there
> I am running SDXL unquantized just fine on my 8GB 1080 (fooocus), with multiple loras. What else is going on that makes this thing run out of VRAM? I...
> [@ameen7626](https://github.com/ameen7626) Excuse me, I explained myself poorly. What I want to achieve is to capture what the main agent is doing, in order to show it. You need to...
> wdym exactly? sub agents should be able to call tools. they should also be logged to langsmith as part of the trace. if you are talking about seeing in...
@nhuang-lc Were you able to look into this?