Instructions to use shaban1911/sd3.5-logit-demo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use shaban1911/sd3.5-logit-demo with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-3.5-medium", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("shaban1911/sd3.5-logit-demo") prompt = "A serene landscape with mountains and a river at sunrise" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Logit-Normal Scheduler Demo

- Prompt
- A serene landscape with mountains and a river at sunrise
Model description
This repo wraps the public Stable Diffusion 3.5-medium model with a custom logit-normal timestep scheduler for biased sampling.
Trigger words
You should use logit to trigger the image generation.
You should use scheduler to trigger the image generation.
You should use diffusion to trigger the image generation.
You should use sampling to trigger the image generation.
Download model
Weights for this model are available in Safetensors,PyTorch format.
Download them in the Files & versions tab.
- Downloads last month
- 18
Model tree for shaban1911/sd3.5-logit-demo
Base model
stabilityai/stable-diffusion-3.5-medium