Transp. Chan

it's like using text to generate scene graphs, one frame per line, containing a bunch of bouding boxes and openpose (if needed)

Is there any paper using llm to do video layout generation?

Are you ready? 🌈 #nijijourney

Is there any paper that uses a token to represent position instead of positional embedding?

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

WOW!!! A GAME FROM NIJI 😍

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）

@DavidSHolz @tekbog szflyin.com/sale-22034156-… Maybe this would help...

@tekbog we will make the orb

all these AI hardware companies and no one has made the orb yet???

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.

Then people write paper about its "emerging" halting problem, LOL

A question that has puzzled me since the days of masked language models. GPTs that can detour insertions to the end of sequence, but is there any LM which predicts the insertion position of evey new token (or even deletion)? Maybe something like diffusion+autoregressive LM?

@C_Sobilac @ddvd233 Join the discord and look at the chat history :)

@ddvd233 @transpchan I ask because I know that some sites have basic animations that any models can use yet How do I make my own animation file from my own video file and online videos?

二次元浓度过高（ #IJCAI

@Yokohara_h I am (still) working on it. :)

Stable DiffusionでVRoidの操作画面2。一貫性捨てて前回よりもう少しVRoid感を減らした。VRoidと画像生成すごく相性が良いので将来AIレンダラー搭載するとイラスト用にも使えて面白そう

@yuliangxiu PhDs can reject paper without reading them. GPT has to read every paper word by word carefully

Imagine if 'GPT' could rapidly become an expert in ANY subject, autonomously gathering information from around the world, retaining it indefinitely, and continuously learning 24/7 for centuries on end... We should definitely fire the PhDs and purchase more GPUs

@dragonmeteor I think the method is heavily based on eg3d from nvlabs. If you fit it with your own datasets, I think it will work similarly. Also, I wonder how did they get the CoNR dataset. I didn't even have a chance to release the datasets before I was kicked out LoL.

Well, to be honest, I'm not working on the 3D domain at the moment. -_-' But this is something I want to do eventually.

DAMN!!! This guy beat me to it. T_T

@EMostaque @nerdymomocat @OpenAI any chance you give me some GPUs to build a system that turns manga into anime? twitter.com/transpchan/sta…

@nerdymomocat @OpenAI Anyone there upset at this heel turn who joined to work on the original amazing vision and mission. We are hiring across roles to work on open source AI with lots more positions being uploaded soon: stability.ai/careers Or just join a community and contribute.

Open offer to anyone @OpenAI who actually wants to work on Open AI: We will match your salary, benefits etc but you can work on any open source AI projects you like, ours or others. Collaborate, be open and prioritise good outcomes over self interest: openai.com/blog/introduci…

@8co28 Wow! That's awesome!! Can this technology also be used to fix other flickering stable diffusion videos by simply giving it character sheets instead of LoRA finetuning? Also, can we use arbitrary MMD motion file and untextured models as inputs? This may save the texturing time.

3枚のAI画像を3Dモデルに投影。面白い技術だが、投影する3Dモデルのポリゴンのシルエットがそのまま出るので使用用途を考えるのがちょっと難しい。