Sign In

Flux Blockwise

56

776

24

Verified:

SafeTensor

Type

Checkpoint Trained

Stats

179

0

Reviews

Published

Nov 29, 2024

Base Model

Other

Training

Steps: 1,111,111
Epochs: 1,111

Hash

AutoV2
A435E8CEE1
SDXL Training Contest Participant
Felldude's Avatar

Felldude

License:

Flux Blockwise (Mixed Precision Model)

I had to build several custom tools to allow for the mixed precision model, to my knowledge it is the first built like this.

  • Faster and more accurate then any other FP8 quantized model currently available

  • Works in Comfy and Forge but forge needs to be set to BF16 UNET

  • Comfy load as a diffuser model USE DEFAULT WEIGHT

  • FP16 Upcasting should not be used unless absolutely necessary such as running CPU or IPEX

  • FORGE - set COMMANDLINE_ARGS= --unet-in-bf16 --vae-in-fp32

  • Other then the need to force forge into BF16, (FP32 VAE optionally) it should work the same as the DEV model with the added benefit of being 5GB smaller then the full BF16

It turns out that every quantized model including my own up to this point to my knowledge has been built UN-optimally per blackforest.

Only the UNET blocks should be quantized in the diffuser model, also they should be upcast to BF16 and not FP16 (Comfy does this correctly)


Hippo Image remix

Lion Image remix

I am currently trying to workout how to follow Blackforest recommendations but using GGUF