Civitai Model Matrix
The Civitai models supported by SoloDesk AI are the ones that have been derived from Stable Diffusion 1.x and Stable Diffusion XL.
Since SD1.x and SDXL have already been tested on the reference machine (REF2026), it is likely that any SD1.x/SDXL model can be supported.
The models in the information matrix are a few that have been tested and known to work. These represent only a small subset of what can be found the Civitai website. Therefore, it is by no means an exhaustive list. The model information matrix gets updated periodically as new models are added and new testing is performed.
| Model Name | Base Model | Disk (GB, Pre Convert) | Disk (GB, Post Convert) | GPU Memory (GB) | Source | Input/Output | Supported | Description/Status |
|---|---|---|---|---|---|---|---|---|
| Real Dream Classic SD1.5 | Stable Diffusion 1.5 | 2.1 | 2.1 | 3.2 | 462367?modelVersionId=717109 | Text+Image+Mask-to-Image | Yes | Tested. |
| AbsoluteReality | Stable Diffusion 1.5 | 2.1 | 2.1 | 3.2 | 81458/absolutereality | Text+Image+Mask-to-Image | Yes | Tested. |
| Natural Sin | Stable Diffusion 1.5 | 2.1 | 2.1 | 3.2 | 25694?modelVersionId=160989 | Text+Image+Mask-to-Image | Yes | Tested. |
| Crystal Clear XL | Stable Diffusion XL | 6.8 | 6.9 | 8.2 | 277058?modelVersionId=1920523 | Text+Image+Mask-to-Image | Yes | Tested. |
| HuslyoRealismXL | Stable Diffusion XL | 6.8 | 6.9 | 8.2 | 1802228/huslyorealismxl | Text+Image+Mask-to-Image | Yes | Tested. |
| GonzaLomo XL | Stable Diffusion XL | 6.8 | 6.9 | 8.2 | 1513492?modelVersionId=2439232 | Text+Image+Mask-to-Image | Yes | Only use Non-DMD version. |
| Dream Shaper XL | Stable Diffusion XL | 6.8 | 6.9 | 8.2 | 112902/dreamshaper-xl | Text+Image+Mask-to-Image | Yes | Tested. |
| Juggernaut XL | Stable Diffusion XL | 6.8 | 6.9 | 8.2 | 133005?modelVersionId=1759168 | Text+Image+Mask-to-Image | Yes | Tested. |
| Real Dream Pony 20 XL | Pony | 6.8 | 6.9 | 8.2 | 153568?modelVersionId=2129811 | Text+Image+Mask-to-Image | Yes | Tested. |
For the Hugginface models, the user runs the Huggingface downloader utility to obtain models. For Civitai models, the user downloads the model (as a single large file) from the Civitai website with a web browser and then converts the file to the Huggingface Diffusers format (a directory with multiple files and subdirectories) using the converter utility. These utilities are invoked from a menu in the SoloDesk user interface.
Note that the GPU memory consumption will have some variance based on the mode in which the model operates. Different operational modes are consist of text-to-image, image-to-image, image+mask-to-image, as well as bfloat16, float16 or float32.
View Supported Huggingface Models