Noise Result

[simonmecho]

Hello, I'm trying the workflow using fp8 and also the gguf version, but in both case I just got result of noise only, what was the case for that? please see the attached screenshot. Thanks!

[baizh0u]

It's a bit strange indeed. Is there any error message in the terminal?
or try .bin format model instead.

[simonmecho]

Actually I've already tried the .bin model, and in both cases there is no errors on the console, which is quite weird...

[chenheng0620]

这是什么情况？？？？怎么解决

[baizh0u]

uugf model or the normal one?

[kakachiex2]

And the generation take forever is really slow

[baizh0u]

try using non-uugf format model with hyper-flux lora.

[kakachiex2]

_Here is my workflow can you give it a check :: | there are 3 workflow | CNet Union | MistoLine | Xlabs | ::

[baizh0u]

It looks quite ok, have you ever tried our example workflow?

[kakachiex2]

Yes same result

[baizh0u]

You guys using Lora with clip port or only use load only Lora weight?

[kakachiex2]

I was using model only load lora, I bypass the lora node and the result is the same, the ksampler take a lot of time to render.

• Loader 445.20s
• Ksampler 1943.20s

[baizh0u]

What kind of gpu are you using? And what is your PyTorch version? Rafael Nolasco ***@***.***>於2024年9月4日 23:14寫道： I was using model only load lora, I bypass the lora node and the result is the same, the ksampler take a lot of time to render. Loader 445.20s Ksampler 1943.20s —Reply to this email directly, view it on GitHub, or unsubscribe.You are receiving this because you commented.Message ID: ***@***.***>