Text-to-Image
Diffusers
Safetensors
MageFlowPipeline
ajh
mage-flow
mage-flow-nvfp4-balanced-ajh
nvfp4
blackwell
qwen3-vl
quantization
balanced
Instructions to use ajh-code/Mage-Flow-NVFP4-Balanced-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-Balanced-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-Balanced-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 vae/config.json from ajh-code/Mage-Flow-NVFP4-Balanced-AJH: direct link, hf CLI and curl.
- Browser
- Download file 112 Bytes
-
https://huggingface.co/ajh-code/Mage-Flow-NVFP4-Balanced-AJH/resolve/main/vae/config.json
- Command line
-
hf download hf://ajh-code/Mage-Flow-NVFP4-Balanced-AJH/vae/config.json
-
curl -L -o config.json https://huggingface.co/ajh-code/Mage-Flow-NVFP4-Balanced-AJH/resolve/main/vae/config.json
112 Bytes
| { | |
| "_class_name": "MageVAE", | |
| "latent_channels": 128, | |
| "downsample_factor": 16, | |
| "sample_posterior": false | |
| } |