arxiv:2508.21058
Lvmin Zhang PRO
lllyasviel
AI & ML interests
None yet
Recent Activity
authored a paper 20 minutes ago
Packing Input Frame Context in Next-Frame Prediction Models for Video
Generation authored a paper 21 minutes ago
Mixture of Contexts for Long Video Generation submitted a paper 6 months ago
Pretraining Frame Preservation in Autoregressive Video Memory CompressionOrganizations
models 49
lllyasviel/FramePack_F1_I2V_HY_20250503
Updated • 9.45k • 44
lllyasviel/FramePackI2V_HY
Updated • 56.5k • 129
lllyasviel/flux_redux_bfl
Updated • 216 • 9
lllyasviel/FLUX.1-schnell-gguf
Text-to-Image • 12B • Updated • 5.82k • 33
lllyasviel/FLUX.1-dev-gguf
Text-to-Image • 12B • Updated • 6.79k • 113
lllyasviel/flux1-dev-bnb-nf4
Updated • 752
lllyasviel/flux_text_encoders
Updated • 49
lllyasviel/flux1_dev
Updated • 167
lllyasviel/paints_undo_single_frame
Text-to-Image • Updated • 8 • 28
lllyasviel/paints_undo_multi_frame
Updated • 20
datasets 0
None public yet