BitsFusion: 1.99 bits Weight Quantization of Diffusion Model

Sergey Tulyakov, Bo Yuan, Jian Ren, Yang Sui, Anil Kag, Yanyu Li, Yerlan Idelbayev, Junli Cao, Ju Hu, Dhritiman Sagar

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.

Repositories linked to this paper

huggingface/diffusers — marked official in Papers with Code; named in the paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Images generated from full-precision Stable Diffusion v1.5. Bottom: Images generated from BitsFusion, where the weights of UNet are quantized into 1.99 bits, achieving 7.9× smaller storage than the one from Stable Diffusion v1.5. All the images are synthesized under the setting of using PNDM sampler [49] with 50 sampling steps and random seed as 1024. Prompts and more generations are provided in App. M.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2406.04333")
get_code_for_paper("2406.04333")
have("2406.04333")

Connect an agent — have() is free.