try first and last frame same again #photoai

run new talking video workflow #photoai

change talking video pipeline for [ Talking video ] on static image to not use Omnihuman (img2video) but instead first make a video (img2video) then Lipsync it #photoai

try video model with same first frame + last frame so we can make better looping talking videos #photoai

change scrolling behavior on new user page where it forces them to first train a model #photoai

email users who didn't train model yet after 24 hours #photoai

try more complex products like Electrolux water purifier #photoai

make product video for Feefty by @marcantoinefon #photoai

make slop for @johnonolan #photoai

show hairdresser #photoai and he wants me to try it on Wella Hairspray in the shop so I did

make talking video for @marving_with_g's book on X to show it works on anything #photoai

make auto detect prompt work for [ Hold a product ] mode #photoai

make the CSS and HTML for the hold product mode #photoai

prototype design of "Hold a product" feature #photoai

fix crop modal floating point issues at edge #photoai

switch #photoai from Flux Kontext for image edits to Qwen Image Edit better model

try Refocus idea to change focus point on photo with Qwen edit and Flux Kontext but it doesn't work on both #photoai

add 0.25x playback speed for photo shoot mode #photoai

send transcript along with ElevenLabs audio to ZapCap for accurate captions #photoai

try combine on #photoai for product placement