Stable-Layers: Fine-Tuning Image Layer Decomposition Models with VLM-Scored Reinforcement Learning
Paper • 2605.30257 • Published • 5
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
View all activity
Papers
Stable-Layers: Fine-Tuning Image Layer Decomposition Models with VLM-Scored Reinforcement Learning
OCTOPUS: Optimized KV Cache for Transformers via Octahedral Parametrization Under optimal Squared error quantization
Question about reprompt feature
1
#7 opened 1 day ago
by 
gemstonebro
mboss
authored 2
papers 1 day ago
mattricesound
updated a
model 1 day ago
Wait..where is the workflow?
1
#6 opened 3 days ago
by gemstonebro
fix README.md: using with stable-audio-3 code block style
2
#1 opened about 1 month ago
by 
ivnvalex
mattricesound
updated 2
models 10 days ago
Can the music I created be used commercially?
2
#5 opened 21 days ago
by 
LordAnuar
CiaraRowles
submitted a
paper to Daily Papers 22 days ago
cortexelus
updated a
model 23 days ago
Support for binaural audio production?
1
#3 opened 29 days ago
by 
GokseninYuksel
[Admin maintenance] Migrate grant to ZeroGPU
#35 opened about 1 month ago
by 
multimodalart
multimodalart
updated 7
Spaces about 1 month ago
TripoSR
🐳
822
Generate a 3D model from a single image
Stable Fast 3D
🎮
1.2k
Generate a 3D mesh from a single image
Stable Audio 3
🎵
114
Text-to-audio with SA3 Medium / Small Music / Small SFX.
Stable Diffusion 3.5 Large Turbo
🏃
420
Generate images fast with SD3.5 turbo
Stable Diffusion 3.5 Medium
🏃
171
Generate images with SD3.5
Stable Diffusion 3 Medium
🎨
1.64k
Generate custom images from text prompts with Stable Diffusion 3
Stable Diffusion 3.5 Large
🏃
2.02k
Generate images with SD3.5