Text-to-Image
Diffusers
Safetensors
English
Chinese
Russian
QwenImage21Pipeline
image-editing
qwen-image
orbitquant
w4a4
4-bit precision
quantized
turbo
few-step
8-bit precision
Instructions to use WaveCut/Turbo-Image-2.1-OrbitQuant-W4A4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use WaveCut/Turbo-Image-2.1-OrbitQuant-W4A4 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/Turbo-Image-2.1-OrbitQuant-W4A4", 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
- Local Apps Settings
- Draw Things
- DiffusionBee
Commit History
23 days ago
-
Store the transformer as fused blocks (OrbitQuant 0.11)
Verified signaturec765d75
29 days ago
-
Rename to Turbo-Image-2.1
Verified signatureae3512a -
Rename to TurboImage2.1
Verified signature6776afe -
Manifest and transformer config: point sources at WaveCut/Image21-Turbo
Verified signature804606b -
Card and scripts: dtype keyword, text encoder layer 6 note
Verified signatureb1b85b3 -
Add files using upload-large-folder tool
Verified signaturedb75a3f -
Add files using upload-large-folder tool
Verified signature926d100 -
initial commit
Verified signaturedbeb732