This is the sd_xl_base_1.0_0.9vae and a LoRA that I made utilizing only the sd_xl_base_1.0_0.9vae and an 800x1000 Transparency Image to make the LoRA; I then merged the sd_xl_base_1.0_0.9vae and the LoRA together to save the Checkpoint, (sd_xl_general_1.0_0.9vae) as a Base Model. I used a transparency image because it contains no data but allows room for data to be input into the resolution of the transparency. By doing this, this way, the only action on the sd_xl base model is a target resolutional resolution of 800x1000 is achieved as nominal resolution. I called it general with the intention that it be used as a general image generation model.
Description
Finished Checkpoint: This was made out of appreciation for the Base Model, which to me is the prototype that makes SDXL possible. The only accompaniment to this model will be the LoRA, (sd_xl_base_1.0_0.9vae_LoRA.safetensors), that was merged with the original Base Model.
Comments (2)
So, what's this for? Generating in 800x resolution?
I use SDXL-compatible resolutions
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.