This page contains scaled fp8 quantized DiT models of Neta Lumina for ComfyUI.<ul><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/1612109">Neta Lumina</a> (NT)</li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/1790792">NetaYume Lumina</a> (NTYM)</li></ul>And a scaled fp8 quantized Gemma 2 2b (the text encoder).All credit belongs to the original model author. License is the same as the original model.Note: Images from bf16 and fp8 models are identical, like <a target="_blank" rel="ugc" href="https://civarchive.com/images/111962921">this</a>. If image from fp8 model changed drastically, your ComfyUI somehow enabled fp16 mode. Lumina 2 doesn't not support fp16, and you will get deformed image.<hr />Update (11/27/2025): mixed precision and fp8 tensor core support (mptc).This is a new ComfyUI feature that supports fp8 tensor core, also with scaled fp8 + mixed precision.In short:Mixed precision: Keep important layers in BF16.FP8 tensor core support: On supported GPU, much faster (30~80%) than BF16 and classic FP8 scaled models. Because ComfyUI will do calculations in FP8 directly, instead of dequantizing + BF16. torch.compile is recommended.More info: <a target="_blank" rel="ugc" href="https://civarchive.com/models/2172944/z-image-turbo-tensorcorefp8">https://civarchive.com/models/2172944/z-image-turbo-tensorcorefp8</a>

Neta Lumina [fp8]

netaLuminaFp8_gemma22b.safetensors

Gemma2 2b

Gemma2 2b mp

Files with SHA256: 577f0128cc57c492a62c6531ca076e56ff6d455149ee7ce38fb43de2dc98d01d