Instructions to use XLabs-AI/flux-RealismLora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use XLabs-AI/flux-RealismLora 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") pipe.load_lora_weights("XLabs-AI/flux-RealismLora") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
how to change the format of the pic?
i want to change the format of the output pic to 1080 x 1920. How can I do that? thanks in advance
You can pass resolution in "Empty Latent Image" node
You can pass resolution in "Empty Latent Image" node
but where can I find it exactly? Sorry, I am absolute beginner
Double click on Comfy UI, search "Empty Latent Image", and add resolution in input fields
You might wanna check setting up Comfy UI videos on YouTube to get familiar with the tool
Format of Pic
in Comfy UI there is a node Call CR Image Output where you can switch output to jpg, png, webp, tif and the best part if you using your train models so you can connect your that trigger name to filename prefix using nodes to CR Image output so your those image will saved with trigger name instead comfyui
this is how I work with empty latent image size where I don't need to change size.
Double click on Comfy UI, search "Empty Latent Image", and add resolution in input fields
You might wanna check setting up Comfy UI videos on YouTube to get familiar with the tool
I only worked with this webtool here. Do I have to download the software?

