Type | |
Stats | 2,791 812 |
Reviews | |
Published | Mar 15, 2023 |
Base Model | |
Training | Epochs: 3 |
Trigger Words | ryanreos realistic photorealistic |
Hash | AutoV2 C3F05B1EFF |
Introduction
A LoRA model trained with ~290 images by RyanReos. The 784mb VAEs (NovelAI, Anythingv3, Orangemix, Counterfeit) are recommended. 0.6 ~ 0.8 weights are good. The preview images are generated using 1.5 version YesMix (because 1.6 version consists of some LoRAs that may affect the results).
Cautions (Must Read)
Some preview images are generated using hires fix. Thus, if you wanna generate the preview images, pls download the original preview images and analyze them using 'PNG INFO' in webui to get all generating information.
The maximum of generating resolution should not exceed 1024 theoretically, otherwise extra/deformed head/limbs will be waiting for you :). Try to use 'hires fix' to prevent this problem and help to generate higher-resolution images.
For 784mb VAEs (NovelAI, Anythingv3, Orangemix, Counterfeit) users, make sure add '--no-half-vae' in command line of webui to prevent generating black images. See voldy's log for the details of edit method. For high-performance GPU, make sure 'medvram' and 'lowvram' mode are disabled.