Back
Similar todos
try new AI image model on #photoai called Flux
See similar todos
take first pics of Flux models #photoai
See similar todos

No replies yet

Move from DALLE3 to FLUX.1 for image generation #life
See similar todos

No replies yet

make sample image generator for the model selector work with Flux #photoai
See similar todos

No replies yet

try more pics with Flux #photoai
See similar todos

No replies yet

try new upscaler for Flux #photoai
See similar todos

No replies yet

replace all the giant prompt stuffing to make photos look good because Flux is just good out of the box #photoai
See similar todos

No replies yet

try retrain SD1.5 model with Flux with the same training ZIP (with stuff like face crop, body crop, stuff that worked for SD1.5) and discover that retraining old SD1.5 models with that training zip won't work well so maybe we should not #photoai
See similar todos

No replies yet

upscale first Flux image with #photoai
See similar todos

No replies yet

nuke public models to upgrade them to Flux #photoai
See similar todos

No replies yet

Adding support for the new FLUX text-to-image model #boltai
See similar todos

No replies yet

try letters with new Flux model combined with Photo AI model #photoai
See similar todos

No replies yet

re-run photo pack samples too with Flux now #photoai
See similar todos

No replies yet

prototype copycat mode (img2img) with Flux because we couldn't make it work before #photoai
See similar todos

No replies yet

try TedX photos with Flux + #photoai
See similar todos

No replies yet

compare stats Flux vs non-Flux photos #photoai
See similar todos

No replies yet

Try out FreeU for better SD images #roomai
See similar todos

No replies yet

Finally played with FLUX to create AI models and then generated try-ons with #fashn model
See similar todos

No replies yet

play around with training FLUX.1 LoRas for specific image styles #wondermachine
See similar todos

No replies yet

deploy new #photoai model pipeline with 1) higher reso, 2) faceswap disabled, we use facefix in pre image before, 3) lora detail disabled, etc
See similar todos