Instructions to use codeanand/pixelcbe-klein4b-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Inference
- Notebooks
- Google Colab
- Kaggle
|
Download README.md from codeanand/pixelcbe-klein4b-lora: direct link, hf CLI and curl.
- Browser
- Download file 981 Bytes
-
https://huggingface.co/codeanand/pixelcbe-klein4b-lora/resolve/main/README.md
- Command line
-
hf download hf://codeanand/pixelcbe-klein4b-lora/README.md
-
curl -L -o README.md https://huggingface.co/codeanand/pixelcbe-klein4b-lora/resolve/main/README.md
981 Bytes
| license: apache-2.0 | |
| base_model: black-forest-labs/FLUX.2-klein-4B | |
| tags: [lora, flux, image-to-image, isometric, pixel-art, maps] | |
| # Pixel Coimbatore painter — FLUX.2 [klein] 4B LoRA | |
| Rank-64 edit-LoRA that turns a flat-shaded isometric city render into the hand-pixelled style of | |
| **[pixelcbe.com](https://pixelcbe.com)**. Trained for 2000 steps (ostris/ai-toolkit, one A100, ~$5) on pairs of | |
| *our own OSM-based base render → painted version of the same render*. | |
|  | |
| - Input: a 1024×1024 base render from [`base/render_v2.py`](https://github.com/Codebrahma/pixelcbe) (same camera and palette). | |
| - Inference: 4 steps, ~1.5 s per tile on an A100 (see `train/modal_train.py::paint`). | |
| - Works best on dense Indian city fabric; terrain, airports, stadiums and flyovers are handled procedurally in the pipeline. | |
| Code: https://github.com/Codebrahma/pixelcbe · Map data © OpenStreetMap contributors. | |
| Use is also subject to the licence of the base model. | |