Build the web for agents, not agents for the web
Paper
•
2506.10953
•
Published
•
9
Get a LLM Assistant personality idea from an image
Memory-Guided Diffusion for Expressive Talking Video Gen
Audio-Driven Portrait Animations
Audio Conditioned LipSync with Latent Diffusion Models
Easily expand image boundaries
torchao
Int8WeightOnlyConfig
is already working flawlessly in our tests.import spaces
from diffusers import FluxPipeline
from torchao.quantization.quant_api import Int8WeightOnlyConfig, quantize_
pipeline = FluxPipeline.from_pretrained(...).to('cuda')
quantize_(pipeline.transformer, Int8WeightOnlyConfig()) # Or any other component(s)
@spaces.GPU
def generate(prompt: str):
return pipeline(prompt).images[0]