Instructions to use zenlm/zen3-image-fast with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use zenlm/zen3-image-fast with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("zenlm/zen3-image-fast", 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
Restore upstream attribution in NOTICE (FLUX.1-schnell)
#1
by zeekay - opened
The shipped NOTICE reads "Copyright 2025-2026 Zen Authors" and names no upstream, but these weights are a derivative of black-forest-labs/FLUX.1-schnell (Apache-2.0).
Apache-2.0 section 4(c) requires retaining upstream attribution notices in distributed derivative works; section 4(d) requires carrying upstream's NOTICE text where upstream ships one. Replacing upstream's copyright with Zen's drops both.
Evidence of derivation: model card declares base_model: black-forest-labs/FLUX.1-schnell
This PR names the upstream and its true license, and keeps Zen's copyright scoped to Zen's own modifications. One LICENSE + one NOTICE; no license change.