正在加载视频...

视频加载失败

adobe is cooking a new inpainting method that understands context extremely well! ELI5: it can insert stuff with the correct perspective and add/remove connected reflections/shadows 👀

58,662 次观看 • 1 年前 •via X (Twitter)

11 条评论

Dreaming Tulpa 🥓👑 的头像
Dreaming Tulpa 🥓👑1 年前

the thing is called OmniPaint project page: code (coming soon):

Austin Scholar 的头像
Austin Scholar2 年前

The secret to kids learning faster and better has been known since 1960. But it’s been impossible to implement. Technology is just starting to catch up, so we can finally use what we’ve known for years to radically change how we educate kids. Want to learn how? Read this:

Jordan Daniel Chesney 的头像
Jordan Daniel Chesney1 年前

Adobe is so slow to the draw. Any idea when they'll release this? ChatGPT 4o might have already made this outdated.

Dreaming Tulpa 🥓👑 的头像
Dreaming Tulpa 🥓👑1 年前

i wouldn't take my chances and wait for it

Angry Tom 的头像
Angry Tom1 年前

Looks promising 👀

Dreaming Tulpa 🥓👑 的头像
Dreaming Tulpa 🥓👑1 年前

indeed!

Maxwell Allen Blessen 的头像
Maxwell Allen Blessen1 年前

Is this available yet to use?

Dreaming Tulpa 🥓👑 的头像
Dreaming Tulpa 🥓👑1 年前

it's adobe 😅

n0geegee 的头像
n0geegee1 年前

openai and gemini already did it. cheaper.

Coldain 的头像
Coldain1 年前

Would like to see tests of this with OpenAI and Gemini xD bet they could do it

Dreaming Tulpa 🥓👑 的头像
Dreaming Tulpa 🥓👑1 年前

yeah, multimodality is a different beast

相关视频