mit-han-lab/dc-ae-turbo-f32c32-sana-1.1-diffusers
Updated
AI & ML interests
Efficient algorithm, system, and hardware for machine learning.
Recent Activity
View all activity
cjy2003
updated
a
model
2 days ago
cjy2003
published
a
model
2 days ago
cjy2003
updated
a
model
5 days ago
cjy2003
published
a
model
5 days ago
han-cai
authored
6
papers
14 days ago
SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer
Paper
•
2501.18427
•
Published
•
21
Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity
Paper
•
2502.01776
•
Published
•
3
Accelerate High-Quality Diffusion Models with Inner Loop Feedback
Paper
•
2501.13107
•
Published
•
2
SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation
Paper
•
2503.09641
•
Published
•
40
Scaling Vision Pre-Training to 4K Resolution
Paper
•
2503.19903
•
Published
•
42
DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer
Paper
•
2507.04947
•
Published
cjy2003
authored
a
paper
14 days ago
han-cai
authored
a
paper
14 days ago
Lmxyy
updated
8
models
about 1 month ago
mit-han-lab/nunchaku
Text-to-Image
•
Updated
•
93
mit-han-lab/svdq-fp4-flux.1-canny-dev
Image-to-Image
•
Updated
•
66
•
2
mit-han-lab/svdq-int4-flux.1-canny-dev
Image-to-Image
•
Updated
•
239
•
5
mit-han-lab/nunchaku-flux.1-canny-dev
Image-to-Image
•
Updated
•
1.41k
•
2
mit-han-lab/svdq-fp4-flux.1-depth-dev
Image-to-Image
•
Updated
•
97
•
1
mit-han-lab/svdq-int4-flux.1-depth-dev
Image-to-Image
•
Updated
•
258
•
5
mit-han-lab/nunchaku-flux.1-depth-dev
Image-to-Image
•
Updated
•
857
•
2
mit-han-lab/svdq-fp4-flux.1-fill-dev
Image-to-Image
•
Updated
•
225
•
2