This is a merge of the LoRA_Disney Character model that I have posted and the sd_xl_base_1.0_0.9vae.safetensors Base Model. It was created to generate the same results as the LoRA at .8 weight with the negative prompt being the same.<span style="background-color:rgb(26, 27, 30);color:rgb(193, 194, 197);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">The ComfyUI Workflow that is included with the model has a setting of fixed at 0 seed; this is the setting I use to sample everything for best results. You can change that to randomize if you desire to get a variety of depictions, as well as enter more for the positive prompt than just the character's name to add to the generation. I suggest leaving the negative prompt the way it is as it is also adjusted to create a high definition and highly detailed image.

Files with SHA256: 2afb53c6ff8da6c95870a85073543e73bc167a03d7cc69bf23242ad2936c4ef4