Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model
Yuqian Hong
lavinal712
AI & ML interests
Diffusion Models
Multimodal Models
Recent Activity
updated
a collection
19 days ago
Transfusion updated
a collection
19 days ago
Transfusion updated
a model 19 days ago
lavinal712/transfusion-7b Organizations
models 28
lavinal712/transfusion-7b
13B • Updated
• 44
lavinal712/omini-kontext-viton-hd-kontext
Updated
lavinal712/NextStep-1-f8ch16-Tokenizer-diffusers
Updated
• 4
lavinal712/omnitok_pretrain_vitamin_base_all_tokens_vae_embed_dim_32_wo_foundation_model
Updated
lavinal712/omnitok_pretrain_vitamin_base_all_tokens_vae_embed_dim_16
Updated
lavinal712/omnitok_pretrain_vitamin_base_all_tokens_vae_embed_dim_32
Updated
lavinal712/omnitok_pretrain_vitamin_base_all_tokens
Updated
lavinal712/omnitok_pretrain_vitamin_base_siglip
Updated
lavinal712/omnitok_pretrain_vitamin_base_wo_foundation_model
Updated
lavinal712/omnitok_pretrain_vitamin_base_w_augmentation
Updated
datasets 5
lavinal712/viton_hd_kontext
Preview
• Updated
• 15
lavinal712/sudoku3k
Viewer
• Updated
• 3.3k • 4
lavinal712/chemical6k
Viewer
• Updated
• 5.79k • 10 • 1
lavinal712/SAM-LLAVA-55k-canny
Viewer
• Updated
• 55.1k • 30
lavinal712/MolOpt-Instructions-Plus
Viewer
• Updated
• 103k • 16 • 1