Streamtabulous

> I mean one concept with generated prompts and option "From text file per sample" and another with the option "from single text file" where you select your unique text...

> I've been experimenting in my free time with these. If I'm able to find the time later in this week I'd be willing to start working on such a...

> An update for anyone interested in this as a feature: > > Got comfortable with blip3 setup and have looked through the OneTrainer source. Will implement soon, just looking...

>  20 steps, my 3070 graphics card takes 1050 seconds, it's too slow!!! ouch you have something going on, my rtx3060 8gig is 5min tops on 1024x1024 and i...

omg what magic is in forge, 54sec while using YouTube 

> On my system NF4-v1 is significantly faster than any other implementation of FLUX (even GGUF Q4, or than NF4-v2 on Forge), but I have a strange bug where the...

> maybe in 6 months but i doubt it https://openart.ai/workflows/cgtips/comfyui---flux-nf4-model---lighter-and-faster/xgXUBq2E14uoHdyx2LTe https://www.youtube.com/watch?v=L5BjuPgF1Ds it happen, just need acly to add the support

>  I found that my laptop 3070 graphics card 8GB can also calculate, and it takes about 70 seconds to capture a 1024 resolution image 70sec is quick, normal...

> NF4 still uses ~10.5GB on my system. I am not sure it will fit entirely into 8GB. (It will probably work, but very slow) i get 5min on schnell...

how did you get it to see the model v1.22 its not seeing it for me same with sdxl v3