Diffusers
Safetensors
OrbitQuantComponentArtifact
orbitquant
quantized
diffusion-transformer
8-bit precision
Instructions to use WaveCut/FLUX.2-klein-4B-OrbitQuant-W3A3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use WaveCut/FLUX.2-klein-4B-OrbitQuant-W3A3 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("WaveCut/FLUX.2-klein-4B-OrbitQuant-W3A3", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
| { | |
| "quant_method": "orbitquant", | |
| "weight_bits": 3, | |
| "activation_bits": 3, | |
| "rotation": "rpbh", | |
| "rotation_seed": 0, | |
| "block_size": "paper", | |
| "codebook": "lloyd_max", | |
| "codebook_version": 2, | |
| "codebook_dtype": "float32", | |
| "row_norm_dtype": "bfloat16", | |
| "activation_norm_dtype": "float32", | |
| "activation_eps": 1e-10, | |
| "weight_pack_dtype": "uint8", | |
| "target_policy": "flux2", | |
| "adaln_policy": "int4_rtn", | |
| "adaln_group_size": 64, | |
| "modules_to_not_convert": [], | |
| "modules_dtype_dict": {}, | |
| "artifact_format_version": 1, | |
| "runtime_mode": "auto_fused", | |
| "activation_kernel_backend": "auto", | |
| "packed_matmul_block_m": 64, | |
| "packed_matmul_block_n": 64, | |
| "packed_matmul_block_k": 128, | |
| "packed_matmul_num_warps": 4 | |
| } | |