Signorlimone comments

Results 4 comments of


                                            Signorlimone

[Bug]: AssertionError: No inf checks were recorded for this optimizer.

For me the problem was the name of my embedding. It was \_example\_ and the underscores doesn't work if immediately succeded by a comma. The solution was to use [name]...

[Bug]: Textual Inversion keeps getting "AssertionError: No inf checks were recorded for this optimizer."

For me the problem was the name of my embedding. It was \_example\_ and the underscores doesn't work if immediately succeded by a comma. The solution was to use [name]...

Using FP8 mixed-precision in accelerate give error. Where and how do I install the necessary packages?

> fp8 is already used in FLUX.1 LoRA training. transformer_engine is included in Accelerate. Therefore, it would be quite difficult to train with 8GB. true, but I was able to...

[Sharing Experience] Training Z-Image LoRA using 12G VRAM ~ 😁

> [@juntaosun](https://github.com/juntaosun) Thank you for sharing your information. This was very usefull. After some testing I got 1024 resolution running on my RTX 3060 with 12 GB VRAM. I used...