Instructions to use rain1011/pyramid-flow-miniflux with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use rain1011/pyramid-flow-miniflux with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("rain1011/pyramid-flow-miniflux", 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
768p Will you post the model soon?
768p Will you post the model soon?
Soon, it will come in this week.
Thanx 4 Your work :) May I ask U if the coming soon 768 checkpoint will arrive under miniflux or sd3 format? Thanx 👌🏻🙏🏻
We have released the 768p miniflux checkppint
Thanx a lot! I've downloaded the model but still there's the message "Error initializing model: The pyramid_flux does not support high resolution now, we will release it after finishing training". Any suggestion?
You should update the code with the latest commit.
Thanx a lot ❤️ . Yes I’ve updated the commit. Unfortunately 768 version apparentely doesn’t work in my system (12 gb vram 3060 + 24 ram) because after several minutes it goes with “out of memory error” and opt split mem min 128 doesn’t work neither causing the crash. I’ve noticed image-to-video 384 also stucks on the 100% of the progression bar but it doesn’t get any mp4 file in the end. Any suggestions?