Text-to-Image
Diffusers
Safetensors
Flux2KleinPipeline
1-bit
gemlite
hqq
cuda
diffusion
flux
prismml
bonsai
Instructions to use prism-ml/bonsai-image-binary-4B-gemlite-1bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use prism-ml/bonsai-image-binary-4B-gemlite-1bit with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("prism-ml/bonsai-image-binary-4B-gemlite-1bit", 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
android
#2
by JNK333 - opened
will there ever be proper android support for gpu or NPU? this model is quite good and ive been waiting for awhile, having it take 5-8 mins on cpu only for 512x512 images sucks especially when i see ios devices generating these 512x512 images in mere seconds on a 17 pro max, i would be great if this was compiled for qnn and i could run it in a dedicated prism-ML app or even local dream on android, i have a cooler and bypass charging so im willing to even test it for you guys on my S24 ultra