InvokeAI/invokeai/backend/flux
2024-08-29 19:08:18 +00:00
..
modules Replace swish() with torch.nn.functional.silu(h). They are functionally equivalent, but in my test VAE deconding was ~8% faster after the change. 2024-08-26 20:17:50 -04:00
math.py Attribute black-forest-labs/flux for much of the flux code 2024-08-26 20:17:50 -04:00
model.py Attribute black-forest-labs/flux for much of the flux code 2024-08-26 20:17:50 -04:00
sampling.py Tidy variable management and dtype handling in FluxTextToImageInvocation. 2024-08-29 19:08:18 +00:00
util.py Run ruff 2024-08-26 20:17:50 -04:00