stable diffusion xl inpainting 1.0 needs about 4.9 GB of memory at Q4_1 (a 3.9 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 4 quants, from 3.8 GB (Q4_0) to 6.9 GB.
Stable Diffusion XL Inpainting 1.0 – text‑to‑image diffusion model with mask support
Stable Diffusion XL Inpainting 1.0 is a latent diffusion model for generating and modifying images from text prompts. It adds inpainting capability with a mask. The model is based on stabilityai/stable-diffusion-xl-base-1.0 and released under the openrail++ license.
Good at
- High‑resolution image generation
- Inpainting with masks
- Text‑driven image editing
Limits
- No vision support beyond inpainting
- Requires 8k context for full performance
- Experimental support only for llama-box v0.0.98+
Best for
- Creating photo‑realistic images from prompts
- Editing existing images with masks
- Research on diffusion inpainting
Who it’s for. Researchers and developers who need a diffusion model for image generation and inpainting. The model is intended for research purposes only and requires compatible inference tooling.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 3.8 GB | 4.7 GB | Fits | Get file → | |
| Q4_1 | 3.9 GB | 4.9 GB | Fits | Get file → | |
| Q8_0 | 4.9 GB | 6.0 GB | Fits | Get file → | |
| — | 6.9 GB | 8.3 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 (file size 3.77 GB, estimated memory 4.7 GB). For 12 GB VRAM, Q4_1 (3.91 GB, 4.9 GB). For 16 GB VRAM, Q8_0 (4.87 GB, 6 GB). The unknown quant is larger and needs 8.3 GB memory at 8k context.
What GPU do you need for stable diffusion xl inpainting 1.0?
These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is Q8_0 (4.9 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.9 GB file, about 6.0 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (6.9 GB file, about 8.3 GB in use).
Which stable diffusion xl inpainting 1.0 quant should you choose?
Q4_1 (3.9 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is Q4_0 at 3.8 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about stable diffusion xl inpainting 1.0
How much VRAM does stable diffusion xl inpainting 1.0 need?
About 4.9 GB at Q4_1 with an 8K context window. That is the 3.9 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run stable diffusion xl inpainting 1.0 on an 8 GB GPU?
Yes, with Q8_0: the 4.9 GB file needs about 6.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of stable diffusion xl inpainting 1.0 GGUF?
It depends on the quant: Q4_0 is 3.8 GB, Q4_1 is 3.9 GB, Q8_0 is 4.9 GB, file is 6.9 GB.
Where can I download stable diffusion xl inpainting 1.0 GGUF?
The files are on Hugging Face in the gpustack/stable-diffusion-xl-inpainting-1.0-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does stable diffusion xl inpainting 1.0 use?
Hugging Face lists the license as openrail++. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run this model on 8 GB VRAM?
Yes, the Q4_0 quant uses 3.77 GB file size and requires about 4.7 GB memory at 8k context, fitting within 8 GB VRAM.
Does this model support image‑to‑image editing?
The model includes inpainting with a mask, enabling image editing based on text prompts.
Is the model free to use?
It is released under the CreativeML Open RAIL++-M license, allowing research use with the specified license terms.