Bagheera's picture

Bagheera PRO

bghira

·

bghira

AI & ML interests

None yet

Recent Activity

new activity 8 days ago

F16/z-image-turbo-masked-dpo:how is the global loss applied?

new activity 9 days ago

AuraDiffusion/16ch-vae:Training, and why fp16?

updated a model 4 months ago

bghira/z-image-turbo-Domokun-scheduled-sampling

View all activity

Organizations

upvoted a collection about 2 years ago

Terminus XL

v-prediction SDXL clone with zero-terminal SNR noise schedule • 8 items • Updated Apr 24, 2024 • 7

upvoted a paper about 2 years ago

PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

Paper • 2403.04692 • Published Mar 7, 2024 • 40