|
|
--- |
|
|
pipeline_tag: text-to-image |
|
|
library_name: diffusers |
|
|
--- |
|
|
|
|
|
A small selection of quantized SDXL models in GGUF format, to be used with the custom ComfyUI nodes from https://github.com/city96/ComfyUI-GGUF |
|
|
|
|
|
| Model | Hugging Face | CivitAI | |
|
|
| ----- | ------- | ------------ | |
|
|
| CyberRealistic XL v4 | [hf link](https://huggingface.co/cyberdelia/CyberRealisticXL) | [civit link](https://civitai.com/models/312530?modelVersionId=1198781) | |
|
|
| Juggernaut v11 | [hf link](https://huggingface.co/RunDiffusion/Juggernaut-XI-v11) | [civit link](https://civitai.com/models/133005?modelVersionId=782002) | |
|
|
| RealVisXL 4.0 | [hf link](https://huggingface.co/SG161222/RealVisXL_V4.0) | [civit link](https://civitai.com/models/139562?modelVersionId=344487) | |
|
|
| RealVisXL 5.0 | [hf link](https://huggingface.co/SG161222/RealVisXL_V5.0) | [civit link](https://civitai.com/models/139562?modelVersionId=789646) | |
|
|
| SDXL 1.0 | [hf link](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) | | |
|
|
| ZavyChroma 5.0 | [hf link](https://huggingface.co/GraydientPlatformAPI/zavychroma5-xl) | [civit link](https://civitai.com/models/119229?modelVersionId=362861) | |
|
|
| ZavyChroma 10.0 | [hf link](https://huggingface.co/misri/zavychromaxl_v100) | [civit link](https://civitai.com/models/119229?modelVersionId=1308507) | |
|
|
|
|
|
These are made with llama-quantize from [llama.cpp b3600](https://github.com/ggerganov/llama.cpp/releases/tag/b3600) patched with https://github.com/city96/ComfyUI-GGUF/blob/main/tools/lcpp.patch |
|
|
|
|
|
A couple of models are quantized with [llama.cpp b3962](https://github.com/ggerganov/llama.cpp/releases/tag/b3962) patched with lcpp_sd3.patch instead, which may give slightly different results than the default b3600-quantized ggufs but not necessarily better. These are marked in the filenames; most users won't need these. |
|
|
|
|
|
It seems that Q4_0 often gives good results for SDXL models, usually coherent but not always consistent with ones from an unquantized model. Adding Q5_K_M because it sometimes gives results clearly closer to the original F16 than Q4. |
|
|
|
|
|
Repo includes basic clip-l and clip-g, and also an improved SDXL VAE called xlVAEC_c91, found here: https://civitai.com/models/152040?modelVersionId=360299 which can be recommended as it seems to give better colors, contrast and details compared to base. |
|
|
|
|
|
If model creators or others wish to have any GGUF files added or removed, I will consider such requests when I see them. |
|
|
|
|
|
--- |
|
|
|
|
|
There are also quantized models uploaded by another user at https://huggingface.co/Old-Fisherman/SDXL_Finetune_GGUF_Files |
