Text-to-Image
Diffusers
Safetensors
StableDiffusionXLPipeline
stable-diffusion
sdxl
fluetnly-xl
fluently
trained
Instructions to use fluently/Fluently-XL-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use fluently/Fluently-XL-v2 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("fluently/Fluently-XL-v2", 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
pf16?
#1
by tintwotin - opened
Would it be possible to include a pf16 file in the UNET folder, so I'll be able to run it on 6 GB VRAM?
To run SDXL models on such a small amount of VRAM, you need to use an SSD-1B, as you will get very low performance on regular SDXL models. Thank you for your interest in our models!
ehristoforu changed discussion status to closed
I run most SDXL models just fine - if they're also shared in fp16.
ehristoforu changed discussion status to open
Good afternoon, if you work through AUTOMATIC1111, then in the extensions find “Model Converter”, download it, download the checkpoint from this repo, in the extension select this checkpoint and select the format for conversion fp16 or fp32. Have a good day!