Instructions to use fancyfeast/bigaspv26-training with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use fancyfeast/bigaspv26-training with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("fancyfeast/bigaspv26-training", 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
- Draw Things
- DiffusionBee
Is this going to continue using flow matching?
#1
by MachineMinded - opened
Hey there π
Curious if this will still use flow matching? Also - Z-Image seems like it might be promising, but I'm sure you've already heard... :)
Yeah it's just a tweak on top of 2.5. Trying some things out before v3. I've been on break so haven't touched Z-image yet, but will definitely give it a try.
Love your work, @fancyfeast ! Is v2.6 training ongoing or are these the final checkpoints? It looks like samples_39997440 is the most-trained iteration, yeah?
Merry Christmas, by the way π