A man presenting at a conference or seminar, focusing on the topic "NUWA-XL: Recursive interpolations for generating very long videos." The slide on the screen details the "Mask Temporal Diffusion (MTD)" model, a diffusion model for global and local diffusion models, highlighting components like "CLIP text Enc," "Time Enc," and various convolution and up block layers. The slide also mentions "Masking visual conditions" with global and local diffusion strategies. Attendees in the audience are attentively listening to the presentation. The environment suggests a professional setting with technical equipment and a formal arrangement.
Text transcribed from the image:
NUWA-XL
Recursive interpolations for generating very long videos
Mask Temporal Diffusion (MTD)
• A basic diffusion model for global & local diffusion models
CEN(0,1)
L Prompts
V
CLIP text Enc
Timestep-U(1,7)
V
Time Enc
d.
d
mask
middle frames
W%
T-KLVAE Enc
T-KLVAE Enc
MSE Loss
A
€0(x2)
DownBlock
Itout
UpBlock
SAN
ˇˋ
DownBlock
Conv Down
ˇˋ
UpBlock
Masking visual conditions
DownBlock
Conv Down
UpBlock
SA
Global diffusion: mask all
Local diffusion: mask middle frames
DownBlock
Conv Down
UpBlock
MidBlock
A
P
→Diffusion Process
→ Visual Condition
→ Prompts
→Timesteps
Yin et al., "NUWA-XL: Diffusion over Diffusion for extremely Long Video Generation," arXiv 2023.
Copyright Mike Shou, NUS
MUM
PANCY
12