Mar 16

1. 10:22

   fix: correct CUDA base image tag to 12.4.1

   H-Liu1997
   3042363
2. 10:19

   fix: upgrade to CUDA 12.4 + torch>=2.6 for CVE-2025-32434 compat

   H-Liu1997
   c5fa989
3. 10:14

   fix: pin transformers<5 for google/umt5-base compat (no model_type in config)

   H-Liu1997
   975c258
4. 10:08

   fix: remove pre-download step, model downloads at runtime startup

   H-Liu1997
   da265c6
5. 10:04

   fix: add diffusers, ftfy, regex deps from model dependency tree

   H-Liu1997
   e153101
6. 10:00

   fix: add omegaconf and safetensors deps required by model

   H-Liu1997
   21a7038
7. 09:57

   fix: add lightning dependency required by model

   H-Liu1997
   ff0b1d9
8. 09:53

   fix: split pip install to avoid index-url conflict for non-torch packages

   H-Liu1997
   c62140b
9. 09:45

   feat: initial FloodDiffusion streaming demo for HF Space⁠

   H-Liu1997 +1: Claude Opus 4.6 (1M context)
   a4f8eb3