Instructions to use Freepik/flux.1-lite-8B-alpha with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Freepik/flux.1-lite-8B-alpha with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Freepik/flux.1-lite-8B-alpha", 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
add AIBOM
#17 opened 8 months ago
by
RiccardoDav
Training Cost
2
#16 opened about 1 year ago
by
zhangyang-0123
Any further development for this?
๐ฅ 2
2
#15 opened over 1 year ago
by
lodestones
Sdcpp integration
๐ฅ 1
2
#14 opened over 1 year ago
by
stduhpf
What layers are skipped?
๐ 1
1
#13 opened over 1 year ago
by
lavinal712
Config.json file missing
#12 opened over 1 year ago
by
sakshamjoshi129
GUIDE to run on LOW VRAM here -tested on 16GB card
โค๏ธ 1
1
#11 opened over 1 year ago
by
froilo
Is there a Lora version of this model?
4
#10 opened over 1 year ago
by
Vigilence
having trouble making this work with loras
14
#9 opened over 1 year ago
by
swwww55
Possible to work with 8GB VRAM and 16GB RAM?
4
#7 opened over 1 year ago
by
krigeta
Do you have plans to support the stabilizability/table diffusion-3.5-large or Jimmy Carter/LibreFLUX models for this model
๐ 1
1
#5 opened over 1 year ago
by
michaelj
Even the 8B model makes many consumer-grade graphics cards unable to run smoothly
๐ 4
6
#3 opened over 1 year ago
by
jian2023
A theoretical formulation of how this works based on a paper by Sakana AI
๐โค๏ธ 7
1
#2 opened over 1 year ago
by
NagaSaiAbhinay