--- tags: - text-to-image - lora - diffusers - template:diffusion-lora widget: - output: url: images/00237-28849255891.png text: '-' - output: url: images/00719-1526459044.png text: realistic, masterpiece, best quality, soft lighting, parameters: negative_prompt: >- bad hands, bad fingers, simple background, logo, signature, copyright text, blur, looking at viewer, high contrast, - output: url: images/00740-2508776112.png text: realistic, masterpiece, best quality, soft lighting, parameters: negative_prompt: >- bad hands, bad fingers, simple background, logo, signature, copyright text, blur, looking at viewer, high contrast, - output: url: images/realistic filter 2.png text: '-' base_model: stablediffusionapi/smooth-mix-v2-ilustrious2 instance_prompt: realistic license: cdla-permissive-2.0 --- # realistic_filter ## Model description This is a lora that helps realistic image generation, you can use my checkpoint to get the results I posted below (yomama 2.5D [Illustrious] [Pony] - Illustrious v1.0 | Illustrious Checkpoint | Civitai). This checkpoint can generate 2.5D results pretty well, but the face tends to be more anime/cartoonish, it can hardly generate realistic image; with this filter, we can shift the balance to a more realistic result. ![712d82bf-b51e-44b1-be60-29405325f74d.jpeg](https://cdn-uploads.huggingface.co/production/uploads/663e3e78c719b0b8a386f24e/E0-GLGmGPhIo77ZAZsDcQ.jpeg) This lora works on other ckpts too, but the results may vary, you may need to play with the weight a bit. e.g. Illustrious-XL - v0.1 | Illustrious Checkpoint | Civitai ![abceabb5-13e2-47ff-af32-64fe8e10c3b9.jpeg](https://cdn-uploads.huggingface.co/production/uploads/663e3e78c719b0b8a386f24e/y0YAROg7Ua90nGuyyca12.jpeg) e.g. NoobAI-XL (NAI-XL) - Epsilon-pred 1.1-Version | Stable Diffusion XL Checkpoint | Civitai ![b4fbd15f-953a-43d9-b23b-2303b1ce5b83.jpeg](https://cdn-uploads.huggingface.co/production/uploads/663e3e78c719b0b8a386f24e/yjOlslX_328VqlDnj39MX.jpeg) As always, have fun and go break some eggs! p.s. Big thanks to creator @FallenIncursio for giving me advice all the time. 😀 ## Source https://civitai.com/models/1003513/realistic-filter-il?modelVersionId=1124771 ## Credit https://civitai.com/user/yomama123556778 ## Trigger words You should use `realistic` to trigger the image generation. ## Download model [Download](/LyliaEngine/realistic_filter/tree/main) them in the Files & versions tab.