Text-to-Image
Diffusers
Safetensors
MageFlowPipeline
ajh
mage-flow
mage-flow-nvfp4-quality-ajh
nvfp4
blackwell
qwen3-vl
quantization
quality
Instructions to use ajh-code/Mage-Flow-NVFP4-Quality-AJH with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ajh-code/Mage-Flow-NVFP4-Quality-AJH with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ajh-code/Mage-Flow-NVFP4-Quality-AJH", 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
Download examples/comparison_bf16.png from ajh-code/Mage-Flow-NVFP4-Quality-AJH: direct link, hf CLI and curl.
- Browser
- Download file 1.12 MB
-
https://huggingface.co/ajh-code/Mage-Flow-NVFP4-Quality-AJH/resolve/main/examples/comparison_bf16.png
- Command line
-
hf download hf://ajh-code/Mage-Flow-NVFP4-Quality-AJH/examples/comparison_bf16.png
-
curl -L -o comparison_bf16.png https://huggingface.co/ajh-code/Mage-Flow-NVFP4-Quality-AJH/resolve/main/examples/comparison_bf16.png
1.12 MB

- Xet hash:
- 03a356135da5b813f264d9916340eacd3384abc3b440d9ebaa0c667258fcd955
- Size of remote file:
- 1.12 MB
- SHA256:
- d8056e4626b8990242bb9d924983ebdf863b9d175565109cc95d9088e7800989
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.