stabilityai/SAME-L
0.9B • Updated • 18.7k • 26
AI & ML interests
Our vibrant communities consist of experts, leaders and partners across the globe. They are developing cutting-edge open AI models for Image, Language, Audio, Video, 3D and Biology.
Recent Activity
Papers
4Director: Controlling Video World Models with Rigid 3D Geometry
SemanTok: Predictable Semantic Tokens for Efficient Autoregressive Video Generation
mattricesound
updated 9
models about 4 hours ago
stabilityai/SAME-S
0.1B • Updated • 2.41k • 15
stabilityai/stable-audio-3-medium-base
Text-to-Audio • 2B • Updated • 8.55k • 26
stabilityai/stable-audio-3-small-music-base
Text-to-Audio • 0.6B • Updated • 2.73k • 24
stabilityai/stable-audio-3-small-sfx-base
Text-to-Audio • 0.6B • Updated • 1.51k • 11
stabilityai/stable-audio-3-optimized
Text-to-Audio • Updated • 26k • 52
stabilityai/stable-audio-3-small-music
Text-to-Audio • 0.6B • Updated • 18k • 169
stabilityai/stable-audio-3-small-sfx
Text-to-Audio • 0.6B • Updated • 34.7k • 195
stabilityai/stable-audio-3-medium
Text-to-Audio • 2B • Updated • 61.3k • • 376
mboss
authored 2
papers 4 days ago
mboss
submitted a
paper to Daily Papers 4 days ago
vveicao
submitted a
paper to Daily Papers 5 days ago
1·111
#1 opened about 1 month ago
by 
Yun1846205420
cortexelus
updated a
model about 1 month ago
Add T5Gemma SentencePiece tokenizer.model
#8 opened about 2 months ago
by 
shawnbro12345
sm_120 sa3-m: add the fp8 medium-DiT tier (176 fp8 GEMM + 96 bf16 fused MHA, 1.43-1.95x vs fp16mixed)
#7 opened 2 months ago
by 
cortexelus
sm_120 SAME-L: AOT (graph-capturable) engines + tensorRT/README.md
#6 opened 2 months ago
by cortexelus
Fix the bf16 medium DiT: bake RoPE's tables into the graph (clipping 3.112% -> 0.014%)
1
#5 opened 2 months ago
by cortexelus
Rebuild medium DiT fp16-mixed engines (sm_90 + new sm_120): attention now fuses, 4.3x faster
2
#4 opened 2 months ago
by cortexelus