define credits in config to start centralizing them #photoai

write script to fix 34 users affected by talking video bug that set credits to NULL because of dumb (but generally safe) SQL query #photoai

get ElevenLabs Business plan sponsored #photoai so we can get 1000+ voices added

investigate credit lost bug #photoai

add search to voice selector modal #photoai

try new pipeline where we add background audio to the voice to videos for more realism #photoai

fix make talking video modal mobile styling #photoai

fix talking video modal on iPhone makes the video go full screen #photoai

test UGC #photoai

add new locked_prefilled_email to #photoai checkout

add live churn and MRR by counting cancellations immediately (not on cycle end) so we can directly tweak cancel page to reduce churn % #photoai

tell Claude to get its fucking SHIT together #photoai

fix language voice selector #photoai

add background audio to video2video lipsync #photoai

try Wan2.1 training txt2img but it looks a bit overtrained #photoai

get both video2video and img2video work with lipsync with 2 different models so you can get the benefits of high movement video models like Kling 2.1 with lipsync (video2video) and regular lipsync only model (img2video) #photoai

add voice to WAN2.1 LoRa video + interpolation + boomerang loop for 5->10 sec #photoai

interpolate WAN2.1 LoRa video and add 1 extra frame #photoai

try WAN2.1 LoRa trainer inference and it's great but low FPS so we need an interpolator #photoai

change steps to be same for all trainings because more steps seems to create the vertical scanlines problem on Flux turbo trainer #photoai