Flux diffusion model implementation using quantized fp8 matmul & remaining layers use faster half precision accumulate, which is ~2x faster on consumer devices.
Apache License 2.0
210
stars
22
forks
source link
when load certain lora, AttributeError: 'Flux' object has no attribute 'diffusion_model' happened. #34
The lora is https://huggingface.co/XLabs-AI/flux-lora-collection/blob/main/realism_lora.safetensors