Sakura PRO
BiliSakura
AI & ML interests
Remote Sensing
Visual Generation
Recent Activity
updated a model 3 days ago
BiliSakura/JLT-diffusers published a model 3 days ago
BiliSakura/JLT-diffusers updated a model 3 days ago
BiliSakura/ProMoE-diffusersOrganizations
pytorch-image-translation-models implementation
-
BiliSakura/TerraMind-1.0-Tokenizer-NDVI
Feature Extraction • 0.3B • Updated • 4 -
BiliSakura/TerraMind-1.0-Tokenizer-LULC
Feature Extraction • 0.2B • Updated • 5 -
BiliSakura/TerraMind-1.0-Tokenizer-DEM
Feature Extraction • 0.3B • Updated • 1 -
BiliSakura/TerraMind-1.0-Tokenizer-S1RTC
Feature Extraction • 0.3B • Updated • 6
Foundation model for remote sensing building detection
huggingface/transformers implemtation
-
BiliSakura/ViTP-InternVL-1B-General
Image Feature Extraction • 0.3B • Updated • 4 -
BiliSakura/ViTP-InternVL-1B-Med
Image Feature Extraction • 0.3B • Updated • 4 -
BiliSakura/ViTP-InternVL-1B-RS
Image Feature Extraction • 0.3B • Updated • 5 -
BiliSakura/ViTP-Vit-L-300M-General
Image Feature Extraction • 0.3B • Updated • 4
diffusers implementation
A collection of Remote Sensing CLIP models in both huggingface/transformers and huggingface/diffusers text encoder production ready style
pytorch-image-translation-models implementation
huggingface/transformers implemtation
-
BiliSakura/ViTP-InternVL-1B-General
Image Feature Extraction • 0.3B • Updated • 4 -
BiliSakura/ViTP-InternVL-1B-Med
Image Feature Extraction • 0.3B • Updated • 4 -
BiliSakura/ViTP-InternVL-1B-RS
Image Feature Extraction • 0.3B • Updated • 5 -
BiliSakura/ViTP-Vit-L-300M-General
Image Feature Extraction • 0.3B • Updated • 4
-
BiliSakura/TerraMind-1.0-Tokenizer-NDVI
Feature Extraction • 0.3B • Updated • 4 -
BiliSakura/TerraMind-1.0-Tokenizer-LULC
Feature Extraction • 0.2B • Updated • 5 -
BiliSakura/TerraMind-1.0-Tokenizer-DEM
Feature Extraction • 0.3B • Updated • 1 -
BiliSakura/TerraMind-1.0-Tokenizer-S1RTC
Feature Extraction • 0.3B • Updated • 6
diffusers implementation
Foundation model for remote sensing building detection
A collection of Remote Sensing CLIP models in both huggingface/transformers and huggingface/diffusers text encoder production ready style