Transp. Chan (@transpchan) 's Twitter Profile
Transp. Chan

@transpchan

Dreaming about using AI to make anime since 2014. Author of Live3D/CoNR/AttNR.

ID: 1273469267451826176

linkhttps://discord.gg/Md3cykbn36 calendar_today18-06-2020 04:15:22

133 Tweet

507 Followers

1,1K Following

Transp. Chan (@transpchan) 's Twitter Profile Photo

Has anyone applied LoRA to an untrained (just a good enough intialization) large model? Will it better than the small LoRA network alone? It's like randomly projecting the data.

Shawn Presser (@theshawwn) 's Twitter Profile Photo

If you watch one video about ML this year, make it this one. It’s probably the best ML video I’ve ever seen. It ties together so much. I’ve waited years for this. How to make an anime without an animation studio: youtu.be/_9LX9HSQkWo

Transp. Chan (@transpchan) 's Twitter Profile Photo

People are hyped up at openai #sora. Rumor has it that synthetic data is the key to its success. Fun fact: ALL anime are synthesized data becase they never "really" existed. People have trained neural network using them for a decade.

まっくす (@minux302) 's Twitter Profile Photo

こんな感じでラフから線画化するAI作ってます。ご興味ある方いたらリプいただけたら変換します!(大ラフほど荒いものにはまだ対応できていないです。今鋭意学習中)

こんな感じでラフから線画化するAI作ってます。ご興味ある方いたらリプいただけたら変換します!(大ラフほど荒いものにはまだ対応できていないです。今鋭意学習中)
Transp. Chan (@transpchan) 's Twitter Profile Photo

Is there any paper doing image translation with pretrianed rectified flow models? Something like instructNoise2Noise connecting two domians, maybe?