Canter
An efficient, photography-oriented text-to-image model
Preview release
The model is still training. Checkpoints and behavior may change during the preview period, and generation quality is still quite variable.
Current checkpoint: v0003
Example gallery · Getting started · API and inference parameters · Technical report · Releases
ComfyUI custom nodes are available in
ComfyUI-Canter. They use
the package's conditioning, guidance, schedule, solver, preview-projection,
and VAE APIs.
This is a 2 billion parameter indie model trained on a single GPU. It is designed for efficient text-to-image generation with a strong focus on photography, natural scenes, people, objects, and places.
The repository bundles the flow-matching denoiser, text tokenizer with a copy
of the required
SmolLM2-360M weights,
Python package, and Gradio interface. Image decoding uses
data-archetype/dinac_ae_d2
VAE, which is downloaded automatically.
Getting started
Requirements
The release requires:
- Python 3.10 to 3.13
- PyTorch 2.13 (
>=2.13,<2.14) with a compatible CUDA build - an NVIDIA GPU with CUDA and bfloat16 support
- 8 GB VRAM for 1024 by 1024 generation with the default bfloat16 release
- Linux or Windows
Install a CUDA-enabled PyTorch build for your system first. The PyTorch installation selector provides the appropriate command.
Install the latest code and checkpoint
Install the Hugging Face CLI, download the moving main revision, and install
the package in editable mode:
python -m pip install "huggingface-hub>=1.15,<2"
hf download data-archetype/canter --revision main --local-dir canter
cd canter
python -m pip install -e ".[webui]"
main contains the latest Canter code and the current default checkpoint.
Editable installation means that refreshing the same directory updates the
code used by the installed canter-web command.
For Python API use without the Gradio interface, install with
python -m pip install -e . instead.
The default checkpoint stores most weights in bfloat16. Numerically sensitive parameters remain in float32.
Update an existing download
Refresh a directory created with hf download by running:
hf download data-archetype/canter --revision main --local-dir canter
If the package was installed without -e, reinstall it afterwards with
python -m pip install --upgrade "./canter[webui]". A Git clone on the main
branch can instead be updated with git pull; an editable installation
immediately uses the updated checkout.
Start the Gradio interface
Run the application from the downloaded repository:
python app.py --in-browser
app.py loads the weights from its own repository directory and
downloads the latest compatible DINAC-AE-D2 VAE. The interface appears
immediately and reports model loading and PyTorch compilation progress.
During sampling, each output slot receives asynchronous previews from the bundled one-eighth-scale latent-RGB projection. Busy preview work is skipped, so sampling never waits for a browser update. The preview checkbox below the size preset disables this feature.
Positive and negative prompts support (text:weight) emphasis during
inference. The same syntax works through the Python pipeline, Gradio interface,
and Canter ComfyUI text-encode nodes.
Downloaded PNG files contain the prompt, optional negative prompt, effective per-image settings, Canter code version, and numbered checkpoint release as JSON metadata.
See the API and inference manual for recommended settings, guidance modes, sampler advice, prompt weighting, and all generation parameters.
The server listens on port 7860. To select the bind address explicitly:
python app.py --server-name 0.0.0.0 --server-port 7860
Use --server-name 127.0.0.1 to restrict access to the local machine.
After package installation, the interface can also download and run the model directly from Hugging Face:
canter-web --model data-archetype/canter --in-browser
Run python app.py --help or canter-web --help for model revision, weight
dtype, text backend, device, cache, and server options.
The Gradio interface requires a non-empty prompt by default and reports
Please enter a prompt for blank or whitespace-only text. To explicitly allow
unconditional generation, launch it with --allow-empty-prompt:
python app.py --allow-empty-prompt
Generate an image with Python
from canter import CanterPipeline
pipe = CanterPipeline.from_pretrained("data-archetype/canter")
result = pipe(
"A weathered wooden boardwalk descending toward a rugged coastline "
"under a stormy sky"
)
result.image.save("canter.png")
See the API and inference manual for the recommended generation recipe and configuration examples.
Example gallery
See the example gallery.
Limitations
The model has more limited knowledge than larger models. Some concepts may be unknown or undertrained, especially uncommon subjects and specialist domains.
Text rendering is currently undertrained and unreliable.
The model has been trained almost exclusively on photographs. It has seen limited artwork outside a few thousand classical paintings, so results for illustration and other non-photographic styles may be weak or inconsistent.
Responsible use
The model and its outputs are provided without guarantees of accuracy, suitability, or safety. Users are responsible for reviewing generated content and complying with applicable laws, privacy obligations, and third-party rights.
Releases
The installed package supplies the inference code. Remote loading without a revision uses the checkpoint pinned by that package:
pipe = CanterPipeline.from_pretrained("data-archetype/canter")
Select an immutable older checkpoint while retaining the installed code:
pipe = CanterPipeline.from_pretrained(
"data-archetype/canter",
revision="v0001",
)
The web interface supports the same separation:
canter-web \
--model data-archetype/canter \
--revision v0001 \
--in-browser
Running app.py from a tagged standalone download intentionally uses the code
bundled with that historical snapshot. Use the installed canter-web command
as above when testing old weights with current code.
Release tags follow the v0001, v0002, v0003, and later numbering scheme.
Optional full-float32 releases use tags such as v0001-fp32.
See the release table and update instructions.
Documentation
Citation
@misc{canter,
title = {Canter: An Efficient, Photography-Oriented Text-to-Image Model},
author = {data-archetype},
email = {data-archetype@proton.me},
year = {2026},
month = jul,
url = {https://huggingface.co/data-archetype/canter},
}
License
The original weights, architecture, model-specific code, and
documentation are licensed under the ModelGo Attribution-ShareAlike License
2.0 (MG-BY-SA-2.0). Commercial use, modification, redistribution, and hosted
use are permitted subject to its attribution, source-disclosure, and
share-alike conditions. Distributions must retain NOTICE.
The bundled SmolLM2 subset remains under Apache License 2.0. See
LICENSE-APACHE-2.0 and Attribution. DINAC-AE-D2 remains
under the license published in its own repository.