MOSS-Image-SFT-GGUF

This is a GGUF quantized version of MOSS-Image-SFT by OpenMOSS, the 5.1B text-to-image transformer. unsloth/MOSS-Image-SFT-GGUF uses Unsloth Dynamic 2.0 methodology: the `UD-` files are mixed precision, with each layer's type chosen from a measured sensitivity scan and an importance matrix collected while generating images. - Runs in Unsloth Studio and in stable-diffusion.cpp builds that include MOSS-Image (master-975 or newer), on CPU, Mac and GPU. - Only the transformer is in these files. The VAE and tokenizer are unchanged; take them from unsloth/MOSS-Image-SFT-FP8, which carries the upstream diffusers folders byte for byte. The text encoder runs from the stock unsloth/Qwen3.5-9B-GGUF `Qwen3.5-9B-Q8_0.gguf`. **Recommended:** `MOSS-Image-SFT-UD-Q4_K_XL.gguf` (3.42 GB) for most machines: LPIPS 0.213 against 0.294 for `Q4_K_M`. For output closer to bf16 use `UD-Q5_K_XL` (0.121) or `UD-Q6_K_XL` (0.106); `Q8_0` (0.054) is the closest. On a CUDA GPU, Unsloth Studio defaults to the INT8-ConvRot file in unsloth/MOSS-Image-SFT-FP8 (LPIPS 0.058) instead. Pick **MOSS-Image-SFT** in the Images tab and choose a GGUF file from this repo. Unsloth Studio runs MOSS-Image GGUFs with its bundled stable-diffusion.cpp engine and downloads the VAE, tokenizer and Qwen3.5-9B text encoder for you. Defaults: 1024x1024, 50 steps, CFG 3, shift 5.

번역 준비 중입니다. 원문을 표시합니다.