Long-WAM
Efficient-Large-Model
community
AI & ML interests
None defined yet.
Recent Activity
Original LTX-2.3 refiners and the LTX-2.5 extension for MiniMax-H3. https://nvlabs.github.io/Sana/Sol-Refiner/
SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer
-
SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer
Paper • 2605.15178 • Published • 92 -
Efficient-Large-Model/SANA-WM_bidirectional
Image-to-Video • Updated • 129 -
Efficient-Large-Model/SANA-WM_streaming
Updated • 1 -
Efficient-Large-Model/SANA-WM_chunk_causal
Text-to-Video • Updated • 35
Efficient Diffusion LLM
-
Efficient-Large-Model/Fast_dLLM_v2_1.5B
2B • Updated • 2.35k • 14 -
Efficient-Large-Model/Fast_dLLM_v2_7B
333k • Updated • 2.59k • 34 -
Fast-dLLM v2: Efficient Block-Diffusion LLM
Paper • 2509.26328 • Published • 60 -
Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding
Paper • 2505.22618 • Published • 47
HuggingFace Transformers can load us.
SANA-1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer
-
SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer
Paper • 2501.18427 • Published • 27 -
Efficient-Large-Model/SANA1.5_4.8B_1024px
Text-to-Image • Updated • 368 • • 26 -
Efficient-Large-Model/SANA1.5_4.8B_1024px_diffusers
Text-to-Image • Updated • • 20 -
Efficient-Large-Model/SANA1.5_1.6B_1024px
Text-to-Image • Updated • 118 • • 7
⚡️Sana: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
-
Efficient-Large-Model/Sana_1600M_1024px
Text-to-Image • Updated • 1.02k • • 226 -
Efficient-Large-Model/Sana_1600M_1024px_BF16
Text-to-Image • Updated • 3.27k • 14 -
Efficient-Large-Model/Sana_1600M_1024px_BF16_ControlNet_HED
Text-to-Image • Updated • 50 • 1 -
Efficient-Large-Model/Sana_600M_1024px_ControlNet_HED
Text-to-Image • Updated • 46 • 3
Few-step and CFG-distillation LoRAs for MiniMax-H3, Wan2.1-T2V-14B, and Wan2.2-TI2V-5B.
-
Efficient-Large-Model/LongLive-Plug-MiniMax-H3-few-step
Text-to-Video • Updated • 227 • 3 -
Efficient-Large-Model/LongLive-Plug-MiniMax-H3-cfg
Text-to-Video • Updated • 63 • -
Efficient-Large-Model/LongLive-Plug-Wan2.1-T2V-14B-few-step
Text-to-Video • Updated • • 1 -
Efficient-Large-Model/LongLive-Plug-Wan2.1-T2V-14B-cfg
Text-to-Video • Updated • 59 •
SANA-Streaming: Real-time Streaming Video Editing with Hybrid Diffusion Transformer
-
SANA-Streaming: Real-time Streaming Video Editing with Hybrid Diffusion Transformer
Paper • 2605.30409 • Published • 38 -
Efficient-Large-Model/SANA-Streaming
Updated • 2 -
Efficient-Large-Model/SANA-Streaming_bidirectional
Updated • 2 -
Efficient-Large-Model/SANA-Streaming-example-training-dataset
Updated • 169 • 2
🎬 SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer
-
SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer
Paper • 2509.24695 • Published • 56 -
Efficient-Large-Model/SANA-Video_2B_720p
Text-to-Video • Updated • 23 • 30 -
Efficient-Large-Model/SANA-Video_2B_720p_diffusers
Text-to-Video • Updated • 6 -
Efficient-Large-Model/SANA-Video_2B_480p
Text-to-Video • Updated • 42 • 17
NVILA: Efficient Frontier Visual Language Models
Boost AI's Long ability, while keeping Efficient. Models in this collection includes LongVILA, LongVILA-R1, LongLive.
🏃SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation
-
SanaSprint
👁423Ultra fast high quality image generation
-
SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation
Paper • 2503.09641 • Published • 42 -
Efficient-Large-Model/Sana_Sprint_1.6B_1024px
Text-to-Image • Updated • 73 • 21 -
Efficient-Large-Model/Sana_Sprint_0.6B_1024px
Text-to-Image • Updated • 100 • 10
Long-WAM
Few-step and CFG-distillation LoRAs for MiniMax-H3, Wan2.1-T2V-14B, and Wan2.2-TI2V-5B.
-
Efficient-Large-Model/LongLive-Plug-MiniMax-H3-few-step
Text-to-Video • Updated • 227 • 3 -
Efficient-Large-Model/LongLive-Plug-MiniMax-H3-cfg
Text-to-Video • Updated • 63 • -
Efficient-Large-Model/LongLive-Plug-Wan2.1-T2V-14B-few-step
Text-to-Video • Updated • • 1 -
Efficient-Large-Model/LongLive-Plug-Wan2.1-T2V-14B-cfg
Text-to-Video • Updated • 59 •
Original LTX-2.3 refiners and the LTX-2.5 extension for MiniMax-H3. https://nvlabs.github.io/Sana/Sol-Refiner/
SANA-Streaming: Real-time Streaming Video Editing with Hybrid Diffusion Transformer
-
SANA-Streaming: Real-time Streaming Video Editing with Hybrid Diffusion Transformer
Paper • 2605.30409 • Published • 38 -
Efficient-Large-Model/SANA-Streaming
Updated • 2 -
Efficient-Large-Model/SANA-Streaming_bidirectional
Updated • 2 -
Efficient-Large-Model/SANA-Streaming-example-training-dataset
Updated • 169 • 2
SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer
-
SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer
Paper • 2605.15178 • Published • 92 -
Efficient-Large-Model/SANA-WM_bidirectional
Image-to-Video • Updated • 129 -
Efficient-Large-Model/SANA-WM_streaming
Updated • 1 -
Efficient-Large-Model/SANA-WM_chunk_causal
Text-to-Video • Updated • 35
🎬 SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer
-
SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer
Paper • 2509.24695 • Published • 56 -
Efficient-Large-Model/SANA-Video_2B_720p
Text-to-Video • Updated • 23 • 30 -
Efficient-Large-Model/SANA-Video_2B_720p_diffusers
Text-to-Video • Updated • 6 -
Efficient-Large-Model/SANA-Video_2B_480p
Text-to-Video • Updated • 42 • 17
Efficient Diffusion LLM
-
Efficient-Large-Model/Fast_dLLM_v2_1.5B
2B • Updated • 2.35k • 14 -
Efficient-Large-Model/Fast_dLLM_v2_7B
333k • Updated • 2.59k • 34 -
Fast-dLLM v2: Efficient Block-Diffusion LLM
Paper • 2509.26328 • Published • 60 -
Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding
Paper • 2505.22618 • Published • 47
NVILA: Efficient Frontier Visual Language Models
HuggingFace Transformers can load us.
Boost AI's Long ability, while keeping Efficient. Models in this collection includes LongVILA, LongVILA-R1, LongLive.
SANA-1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer
-
SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer
Paper • 2501.18427 • Published • 27 -
Efficient-Large-Model/SANA1.5_4.8B_1024px
Text-to-Image • Updated • 368 • • 26 -
Efficient-Large-Model/SANA1.5_4.8B_1024px_diffusers
Text-to-Image • Updated • • 20 -
Efficient-Large-Model/SANA1.5_1.6B_1024px
Text-to-Image • Updated • 118 • • 7
🏃SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation
-
SanaSprint
👁423Ultra fast high quality image generation
-
SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation
Paper • 2503.09641 • Published • 42 -
Efficient-Large-Model/Sana_Sprint_1.6B_1024px
Text-to-Image • Updated • 73 • 21 -
Efficient-Large-Model/Sana_Sprint_0.6B_1024px
Text-to-Image • Updated • 100 • 10
⚡️Sana: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
-
Efficient-Large-Model/Sana_1600M_1024px
Text-to-Image • Updated • 1.02k • • 226 -
Efficient-Large-Model/Sana_1600M_1024px_BF16
Text-to-Image • Updated • 3.27k • 14 -
Efficient-Large-Model/Sana_1600M_1024px_BF16_ControlNet_HED
Text-to-Image • Updated • 50 • 1 -
Efficient-Large-Model/Sana_600M_1024px_ControlNet_HED
Text-to-Image • Updated • 46 • 3