Based on the pixelated model trained by SD1.5, the larger the weight, the more obvious the pixel style. Keywords can add pixel, pixel art and other enhanced painting style. In addition to characters, it can also generate some elements such as animals and scenes. Both Vincennes diagrams and Tu-sen diagrams have strong stability. More gameplay you can explore on your own.
Welcome to post and share
Size :512 x 768 or 512 x 512. Recommended sampling method: Euler a
Settings: Sampling: 28 steps, weight :0.8-1, DPM++ 2M Karras, CLIP: 2
Trigger: pixel, Pixel style
Description
FAQ
Comments (3)
From the size of the file it seems more like lora file, not full checkpoint. Please fix the type value.
Thanks for the correction. Wrong choice
Hi, which checkpoints do you recommend to use with this LoRA?
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.






