Haopeng Li

hp-l33

·

https://hp-l33.github.io

hp-l33

AI & ML interests

Efficient AI

Recent Activity

updated a Space 1 day ago

hp-l33/ref2v-compare

published a Space 1 day ago

hp-l33/ref2v-compare

updated a dataset 4 days ago

hp-l33/DraftKV_Assets

View all activity

Organizations

updated a Space 1 day ago

Ref2V Compare

HyperFlow-Flash vs Pika-H3-Flex, reference-to-video

published a Space 1 day ago

Ref2V Compare

HyperFlow-Flash vs Pika-H3-Flex, reference-to-video

updated a dataset 4 days ago

hp-l33/DraftKV_Assets

Viewer • Updated 4 days ago • 91 • 1.54k

published a dataset 10 days ago

hp-l33/DraftKV_Assets

Viewer • Updated 4 days ago • 91 • 1.54k

updated a model 10 days ago

Efficient-Large-Model/Sol-H3-VAE

Updated 10 days ago • 7.17k • 10

updated 2 Spaces 11 days ago

Qwen-Image 2.1 Four-Step on M5

Qwen-Image 2.1 4-step LoRAs + W8A8 + TAE on a 24 GB M5 Mac

Sol-Attn2

FP8 sparse attention with a compressed tail

published a Space 12 days ago

Qwen-Image 2.1 Four-Step on M5

Qwen-Image 2.1 4-step LoRAs + W8A8 + TAE on a 24 GB M5 Mac

updated a collection 22 days ago

Sol-H3

MiniMax-H3 video with sound on one RTX 5090 or DGX Spark. Code: github.com/NVlabs/Sana/tree/sol-engine/models/minimax_h3 • 2 items • Updated 22 days ago • 1

published a model 22 days ago

Efficient-Large-Model/Sol-H3-VAE

Updated 10 days ago • 7.17k • 10

updated a dataset 22 days ago

Efficient-Large-Model/Sana-assets

Updated 10 days ago • 76.3k

published a Space about 1 month ago

Sol-Attn2

FP8 sparse attention with a compressed tail

authored a paper about 1 month ago

SoL-Refiner: Speed-of-Light One-Step Refinement for High-Resolution Video

Paper • 2609.37969 • Published Sep 29 • 28

upvoted a paper about 1 month ago

SoL-Refiner: Speed-of-Light One-Step Refinement for High-Resolution Video

Paper • 2609.37969 • Published Sep 29 • 28

published a Space about 1 month ago

FLUX.3 Action · RTX 5090

RTX 5090 优化报告：约 2.05× 加速、质量 gate 与可下载实测证据

upvoted a paper about 2 months ago

SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness

Paper • 2609.20519 • Published Sep 17 • 90

updated a Space about 2 months ago

Sol-Attn 95% Experiments

Explore side‑by‑side video comparisons of diffusion experiments

published a Space about 2 months ago

Sol-Attn 95% Experiments

Explore side‑by‑side video comparisons of diffusion experiments

updated a Space about 2 months ago

MiniMax H3 on DGX Spark

Generate high‑resolution videos from text prompts