The model is fp8 and based on Flux.1D. It comes without VAE, Clip and textencoder to save disc space. So be sure to load those files in your workflow.
Suggest parameters for image generation v1:
Sampler: euler, Scheduler: simple, Steps: 20, Distilled CFG: 3.5
Нас не догонят and Нас не догонят Bø:
Use whatever you like - so do I :-) ... but allways use 12 steps !
Some images come with ComfyUI workflows ...
Quadrigal:
Old wine in a new bottle ;-) ... 14 steps and a little splash of upscale for great results !
Description
FAQ
Comments (3)
How are we supposed to compare this to the base model if you don't include your prompts?
dude newbee come on
it give maybe 20 models which you have merged
and you have permissions ?
which clip and text encoder? The ones I've tried dont work.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.