# ============================================================================= # GPU / Local Diffusion dependencies # Install alongside requirements.txt when running with AI_PROVIDER=local_gpu # # Usage: # pip install -r requirements.txt -r requirements.gpu.txt # # These are pre-installed in Dockerfile.gpu; optional in the standard image. # ============================================================================= # HuggingFace Diffusers ecosystem # Pinned <0.29.0: diffusers 0.29.0 added torch.xpu (Intel GPU) which fails on # PyTorch 2.1.x with "AttributeError: module 'torch' has no attribute 'xpu'". # Upgrade the base image in Dockerfile.gpu to pytorch 2.4+ before lifting this pin. # (FLUX support requires diffusers>=0.29 + PyTorch>=2.4; SDXL/SD works fine here.) diffusers>=0.28.0,<0.29.0 transformers>=4.36.0,<4.40.0 accelerate>=0.27.0 huggingface-hub>=0.23.0 safetensors>=0.4.0 # Required by SDXL pipelines invisible-watermark>=0.2.0 omegaconf>=2.3.0 # Required by FLUX (T5 text encoder tokenizer) sentencepiece>=0.2.0 # xformers — reduces attention VRAM ~20-30%, often unlocks the next model tier # Must match your PyTorch+CUDA version; leave out if unsure. # Install post-container-start if needed: # pip install xformers --index-url https://download.pytorch.org/whl/cu121 # xformers