Diffusers
Safetensors
OrbitQuantComponentArtifact
orbitquant
quantized
diffusion-transformer
8-bit precision
Instructions to use WaveCut/FLUX.1-schnell-OrbitQuant-W2A3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use WaveCut/FLUX.1-schnell-OrbitQuant-W2A3 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.1-schnell-OrbitQuant-W2A3", 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
Commit History
-
Requantize W2A3 with mixed-width low-bit protection
Verified signatureca3ac0f
-
Expand native comparison to ten complex prompts
Verified signaturee65253d
-
Replace artifact with paper-correct codebook v2 and native proof
Verified signature2bfed70 -
Upload OrbitQuant artifact
Verified signatureee6a7d6
-
Publish compact OrbitQuant artifact metadata
Verified signature4235b03 -
Clean OrbitQuant artifact assets
Verified signaturebb62826 -
Keep OrbitQuant model repos focused on final artifacts
Verified signature5c680d5 -
Upload FLUX.1-schnell OrbitQuant W2A3 native visual artifact
Verified signature9755ca9 -
Upload folder using huggingface_hub
Verified signaturea6af2ae
-
Upload FLUX.1 schnell OrbitQuant W2A3 artifact
Verified signatureb271730