Text-to-Image
Diffusers
Safetensors
StableDiffusionXLPipeline
sdnq
noobai
sdxl
4-bit precision
8-bit precision
Instructions to use Disty0/NoobAI-XL-v1.1-SDNQ-uint4-svd-r128 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Disty0/NoobAI-XL-v1.1-SDNQ-uint4-svd-r128 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Disty0/NoobAI-XL-v1.1-SDNQ-uint4-svd-r128", 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
How to quantize a model?
#1
by gabbo1995 - opened
Hi! Thanks for your work and all the models you provide.
I am a bit confused about how to quantize a fine tune of SDXL I own.
Is there a folder you can point me of examples about quantizing models? What are the requirements needed?
Thank you very much!
Just enable SDNQ quantization in quantization settings and save the model after it is done loading from models -> save.
https://github.com/vladmandic/sdnext/wiki/SDNQ-Quantization
Thank you!