Instructions to use black-forest-labs/FLUX.1-dev with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use black-forest-labs/FLUX.1-dev with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- AMD Developer Cloud
- Local Apps Settings
- Draw Things
- DiffusionBee
how to generate image with 4096 to 4096 pixel size
#312
by Bholumh - opened
I tried to generate image with 4096 px size its giving blank image but its generating image with 2048 px size. I wants to know it there any limitation like, this model can generate images upto 2048 px size?
Anyone tried pls reply.
Thanks in advance.
@Bholumh I would probably not recommend generating 2048x2048 but rather generate at 1024x1024, and then upscale it. You will get much better results and much less artifacts.
How can I upscale the image? Please provide any techniques and other solutions to generate a 4096-pixel image.
Anyone tried pls reply.
Thanks in advance.