Pony Diffusion v6 XL GGUF

--- license: creativeml-openrail-m base_model: LyliaEngine/Pony_Diffusion_V6_XL base_model_relation: quantized pipeline_tag: text-to-image tags: [gguf, stable-diffusion, sdxl, image-generation, quantized, off-grid] --- # Pony Diffusion V6 XL — GGUF (Off Grid build) GGUF conversions of [Pony Diffusion V6 XL](https://huggingface.co/AstraliteHeart/pony-diffusion-v6) for **on-device** image generation with [stable-diffusion.cpp](https://github.com/leejet/stable-diffusion.cpp). Converted with sd.cpp's `-M convert` so the tensors are correctly named and load directly — the community GGUF quants of this model are mis-exported and fail `get sd version from file`.  ## Files - `pony-diffusion-v6-xl-Q8_0.gguf` — best quality - `pony-diffusion-v6-xl-Q4_K_S.gguf` — lighter / lower RAM `Q4_K_S` in a file name: stable-diffusion.cpp wrote the file with `--type q4_K`. Its weight tensors are Q4_K and the other tensors stay F16/BF16/F32. `Q4_K_S` is the closest standard GGUF label, so Hugging Face can list the file. This file was named `pony-diffusion-v6-xl-Q4_K.gguf` before 2026-10-21; the contents are unchanged, and links pinned to an earlier commit still work. ## Use with stable-diffusion.cpp ```bash sd -M img_gen -m pony-diffusion-v6-xl-Q8_0.gguf -p "your prompt" -o out.png \ -W 1024 -H 1024 --steps 24 --cfg-scale 5 --sampling-method dpm++2m ``` Built for **Off Grid AI Desktop** — a private, fully on-device AI app ([offgridmobileai.co](https://offgridmobileai.co/)). ## Credit & license **Original model:** https://huggingface.co/AstraliteHeart/pony-diffusion-v6 — created by its respective authors. **License:** `creativeml-openrail-m` (carried over from the original; its use restrictions apply). This is a format conversion (quantization) only; all credit for the model belongs to the original creators.

--- license: creativeml-openrail-m base_model: LyliaEngine/Pony_Diffusion_V6_XL base_model_relation: quantized pipeline_tag: text-to-image tags: [gguf, stable-diffusion, sdxl, image-generation, quantized, off-grid] --- # Pony Diffusion V6 XL — GGUF (Off Grid build) GGUF conversions of [Pony Diffusion V6 XL](https://huggingface.co/AstraliteHeart/pony-diffusion-v6) for **on-device** image generation with [stable-diffusion.cpp](https://github.com/leejet/stable-diffusion.cpp). Converted with sd.cpp's `-M convert` so the tensors are correctly named and load directly — the community GGUF quants of this model are mis-exported and fail `get sd version from file`.  ## Files - `pony-diffusion-v6-xl-Q8_0.gguf` — best quality - `pony-diffusion-v6-xl-Q4_K.gguf` — lighter / lower RAM ## Use with stable-diffusion.cpp ```bash sd -M img_gen -m pony-diffusion-v6-xl-Q8_0.gguf -p "your prompt" -o out.png \ -W 1024 -H 1024 --steps 24 --cfg-scale 5 --sampling-method dpm++2m ``` Built for **Off Grid AI Desktop** — a private, fully on-device AI app ([offgridmobileai.co](https://offgridmobileai.co/)). ## Credit & license **Original model:** https://huggingface.co/AstraliteHeart/pony-diffusion-v6 — created by its respective authors. **License:** `creativeml-openrail-m` (carried over from the original; its use restrictions apply). This is a format conversion (quantization) only; all credit for the model belongs to the original creators.

Source context: 2054 downloads · 3 likes · Pipeline text-to-image · Repo off-grid-ai/pony-diffusion-v6-xl-GGUF