import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Yuvrajxms09/klein-torchao-artifacts", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
FLUX.2 Klein 4B TorchAO NVFP4 artifact
This deployment artifact contains pre-quantized TorchAO NVFP4 weights for the Klein transformer and its reduced 27-layer Qwen text encoder. Activations are quantized dynamically at inference time. The original FLUX.2 Klein 4B repository is still required for the tokenizer, scheduler, and remaining pipeline components. See manifest.json for the exact configuration and package versions.
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support