| --- |
| license: apache-2.0 |
| base_model: |
| - lodestones/Chroma |
| --- |
| |
| `Chroma` is a 8.9 billion parameter rectified flow transformer capable of generating images from text descriptions. |
| Based on `FLUX.1 [schnell]` with heavy architectural modifications. |
|
|
| # It is recommended to use [Scaled FP8](https://huggingface.co/Clybius/Chroma-fp8-scaled/tree/main) or [these updated GGUFs](https://huggingface.co/silveroxides/Chroma-GGUF/tree/main) instead! |
|
|
| Quantized into GGUF format using a modified llama.cpp & city96's ComfyUI-GGUF/tools. Distillation layers are not quantized. |
|
|
| Also see [silveroxides'](https://huggingface.co/silveroxides/Chroma-GGUF) Chroma GGUFs! (BF16, Q8_0, Q6_K, Q5_K_S, Q5_1, Q5_0, Q4_K_M, Q4_1, Q4_0, Q3_K_L) |
|
|
| Q*_M GGUFs are mixed quantizations with an aim at maximizing speed by selectively choosing the quantization of certain layers. |
| - Q8_M focuses on Q8_0 quantization of weights for performance, mixed with Q6_K on less heavy layers. |
