正在加载视频...

视频加载失败

Nvidia presents ConsiStory Training-Free Consistent Text-to-Image Generation paper page: enable Stable Diffusion XL (SDXL) to generate consistent subjects across a series of images, without additional training.

161,673 次观看 • 2 年前 •via X (Twitter)

10 条评论

Furkan Gözükara 的头像
Furkan Gözükara2 年前

We already do this with Dreambooth what is the difference advantage? and still no code :

Cesar Silva 的头像
Cesar Silva2 年前

@Grigomesmo @omisil44

pressed tin 的头像
pressed tin2 年前

things are gonna get wild huh

ari 的头像
ari2 年前

The future of video games is gonna be wild

Vahi Güner 的头像
Vahi Güner2 年前

Important need, character consistency

𝕄𝕚𝕔𝕙𝕒𝕖𝕝 𝕁𝕒𝕞𝕖𝕤 🦅 🇺🇸 的头像
𝕄𝕚𝕔𝕙𝕒𝕖𝕝 𝕁𝕒𝕞𝕖𝕤 🦅 🇺🇸2 年前

🔥

DKRacingFan 的头像
DKRacingFan2 年前

How does it learn without training?

rk⚡fg  的头像
rk⚡fg 2 年前

What would the subject look like if he was...

maru 的头像
maru2 年前

Cool

cardoso 的头像
cardoso2 年前

@artificialguybr

相关视频