Chroma1-HD is a text-to-image diffusion model hosted on Hugging Face. It generates images from text prompts and is distributed as an open-source model under the Apache 2.0 license.
The model is provided through the Diffusers library. Installation uses the command pip install -U diffusers transformers accelerate. Loading occurs with a DiffusionPipeline call that accepts a model identifier of lodestones/Chroma1-HD, sets torch_dtype to bfloat16, and applies device_map for cuda or mps runtimes. A supplied example prompt produces an output image object that can be saved or displayed.
It is compatible with local applications that support the Diffusers pipeline, including Draw Things and DiffusionBee. Notebooks for Google Colab and Kaggle are also referenced as execution environments. The model card lists it under the Text-to-Image task and includes a Safetensors format for weights.
The repository is maintained under the lodestones organization on Hugging Face. No pricing information appears because the model is freely downloadable and runs locally or on supported inference providers.
In the Image generation space, Chroma1 HD takes a focused approach. It focuses on creating detailed, high-resolution images from natural language descriptions using a diffusion pipeline. Chroma1 HD is an open-source project aimed at AI artists and developers. The project is open source (Open Source). It ships for the web, the command line, and API.
Behind Chroma1 HD is lodestones.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do