Jonseed
Jonseed
Maybe this is more of an enhancement than a bug? (Although the slider is really functionless when doing txt2img, so kind of a bug?)
The way it is implemented in Auto/Forge is frontend, and it does seem a bit awkward, and doesn't work all the time (if the tab sleeps it stops working, and...
Ok, good to know. I've played around with several schedulers/samplers with Flux in Auto1111/Forge, and have found some generate much more detailed images than others. For example, DEIS DDIM produces...
Can you say what default scheduler/sampler is currently used for Flux in Invoke? I've also found that DPM++ 2M Beta is a good combination for Flux.
> cannot add vae for Flux (ae.safetensors) > cannot add T5 for Flux Yeah, you have to add a Flux VAE and Flux T5 from the "starter models" tab in...
A workaround is loading one image at a time into the Batch Loader with an incrementer, incrementing the `start_index` and using an `image_load_limit` of 1.
I would also like wildcards, using the ImpactPack wildcard nodes for processing in the format `__wildcard__`. Any prompts with a wildcard (or multiple wildcards) so formatted could be passed to...
A basic short-term solution could be to check if the entered prompt has wildcards (words with double underscores `__` surrounding them), and if so then pass that prompt to a...
Look forward to testing it!
Oh, yeah, that sound much easier. I didn't know the Impact Pack had an API.