Text-to-Image
Diffusers
Safetensors
English
flux
flux2
vae
hdr
ultrahd
cinematic
high-detail
image-enhancement
texture-recovery
sharpness-enhancement
color-enhancement
microcontrast
raw
generative-ai
stable-diffusion
diffusion
latent-space
photorealistic
neural-compression
reconstruction
fp16
inference
image-generation
visual-quality
machine-learning
ai-art
flux-compatible
Instructions to use Felldude/FLUX.2-HDR-VAE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Felldude/FLUX.2-HDR-VAE with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Felldude/FLUX.2-HDR-VAE", 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 Settings
- Draw Things
- DiffusionBee
Real HDR Output?
#2
by aaronth07 - opened
Does this result in real HDR output? As in high dynamic range rendering, for HDR monitors, with an HDR color space (Rec2100 HLG, linearSRGB, etc.)? Or is this just for the "HDR effect" similar to HDR panorama merge in lightroom?
So no monitor on the market can do 16 bits per channel.
But yes the VAE does produce less quantized color but you must output using OpenCV and normalize by 65k not the standard /255 - If pillow touches the workflow it is ruined.