Instructions to use tokenaii/Horus-Lens-1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use tokenaii/Horus-Lens-1.0 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("tokenaii/Horus-Lens-1.0", 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
π© Report: Spam
This repository is presented as a fine-tuned model ("Horus-Lens-1.0") but the
transformer weights are a byte-for-byte copy of the official Alibaba/Tongyi
Z-Image base model (Tongyi-MAI/Z-Image). No fine-tuning has taken place.
Proof β the SHA256 hashes of the transformer safetensors shards are identical:
Official Tongyi-MAI/Z-Image (transformer/):
00001-of-00002: ecd5df7768856215812af84d5cc785ba9d84c6d8c84e6939c7ccf30a2e0d2425
00002-of-00002: e2d5fb75ca504b2d669a33af9380b68e0c1632ecddbfca85f82631958a4b81b1
tokenaii/Horus-Lens-1.0 (horus_transformer/):
00001-of-00002: ecd5df7768856215812af84d5cc785ba9d84c6d8c84e6939c7ccf30a2e0d2425
00002-of-00002: e2d5fb75ca504b2d669a33af9380b68e0c1632ecddbfca85f82631958a4b81b1
Identical SHA256 = identical bytes. Any real training run would change every
tensor and therefore both hashes. These can be verified via the HF tree API
without downloading anything:
https://huggingface.co/api/models/tokenaii/Horus-Lens-1.0/tree/main/horus_transformer
https://huggingface.co/api/models/Tongyi-MAI/Z-Image/tree/main/transformer
This misleads users into downloading 12GB of duplicate weights believing they
are a distinct model. Please review.