Instructions to use ostris/Flex.1-alpha with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ostris/Flex.1-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("ostris/Flex.1-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
Very good model but....
#17
by nz9392 - opened
If this is your Version Alpha for this model, I will not expect anything less when you release the Stable version later on. Compared to Flux.1D, I can make anime characters easily without needing to have LoRA or any other checkpoints installed. However, I noticed the art style is not consistent. Can you suggest any sub-prompts if I am looking for Anime character generation? I have tested with 90s' anime style but this is the only one working. "Waifu" as sample is not mean anything when generating.
nz9392 changed discussion title from Very good model to Very good model but....