Instructions to use telcom/dee-z-image with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use telcom/dee-z-image with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("telcom/dee-z-image", 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
Microscope tooling
Small utilities to inspect this repository’s Diffusers checkpoint without leaving the repo.
Setup
From the repo root:
cd microscope
python3 -m venv .venv
source .venv/bin/activate
pip install -U pip
pip install -r requirements.txt
Usage
Inspect the local model (default: one directory up from this folder) without importing PyTorch/Diffusers:
python inspect_model.py --model-dir .. --config-only
Include parameter counts by scanning *.safetensors headers (still does not load weights into RAM):
python inspect_model.py --model-dir .. --config-only --params
Write a machine-readable summary:
python inspect_model.py --model-dir .. --config-only --params --json-out model_summary.json
Flags:
--model-dir: path to the Diffusers pipeline (default:..).--config-only: read JSON configs and print a summary (recommended).--params: count parameters from*.safetensorsmetadata (no tensor loading).--json-out: write a JSON summary to this path.