FourTune matches full-precision LoRA quality on diffusion post-training via native W4A4G4 with a frozen SVD stabilizer, block-wise quant, and fused kernels, cutting memory 2.25× and speeding training 2.27× on FLUX.1-dev.
International Joint Conference on Natural Language Processing , year =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
FourTune: Towards Fully 4-Bit Efficient Post-Training for Diffusion Models
FourTune matches full-precision LoRA quality on diffusion post-training via native W4A4G4 with a frozen SVD stabilizer, block-wise quant, and fused kernels, cutting memory 2.25× and speeding training 2.27× on FLUX.1-dev.