import torch
from diffusers import DiffusionPipeline
from diffusers.utils import load_image
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("leafmoone/RUM-FLUX.2-klein-4B-ConvRot-Quantized", torch_dtype=torch.bfloat16, device_map="cuda")
prompt = "Turn this cat into a dog"
input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png")
image = pipe(image=input_image, prompt=prompt).images[0]RUM FLUX.2 Klein 4B ConvRot Quantized
Post-training ConvRot quantizations of RUM-FLUX.2-klein-4B-preview, based on FLUX.2-klein-base-4B. The repository provides a quality-first INT8 model and a smaller hybrid INT4 model. RUM's dual text-conditioning projections and sensitive input, output, normalization, and modulation layers remain in BF16.
Files
rum-flux2-int8-convrot-adaround-realcal-hq.safetensors: INT8 ConvRot + AdaRound with real-activation calibration.rum-flux2-int4-hybrid-convrot-adaround-realcal-hq.safetensors: hybrid INT4 ConvRot + AdaRound with real-activation calibration; incompatible or quality-sensitive layers remain BF16.standalone_inference.py: self-contained RUM architecture and quantized runtime entry point for text-to-image and image editing.
Download the FLUX.2 Klein 4B base model and the SDXL/WAI teacher checkpoint separately, then pass their local paths to standalone_inference.py. Run python standalone_inference.py --help for all options. The recommended defaults are 20 steps for text-to-image and 10 steps for editing.
Comparison
- Downloads last month
- 2
Model tree for leafmoone/RUM-FLUX.2-klein-4B-ConvRot-Quantized
Base model
rimochan/RUM-FLUX.2-klein-4B-preview