Text-to-Image
Diffusers
Safetensors
English
Russian
LensPipeline
LensPipeline
sdnq
quantized
uint4
static-quantization
ablation
Instructions to use WaveCut/Lens-Turbo-SDNQ-uint4-static with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use WaveCut/Lens-Turbo-SDNQ-uint4-static 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/Lens-Turbo-SDNQ-uint4-static", 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
-
Add model CPU offload cold and warm benchmark
Verified signature23f4b7d -
Add transformer footprint metric and clean visual section
Verified signature08fc650 -
Deduplicate comparison grid in model card
Verified signaturecea9922 -
Clean stale artifacts and add 1:1 WebP comparison grid
Verified signatureed0c3b0 -
Upload corrected SDNQ uint4 static Lens-Turbo
Verified signaturec5fedc7 -
Upload SDNQ Uint Static quantized Lens-Turbo
Verified signature09f4a4a -
initial commit
Verified signaturec08ce47