Models>
Ed Sheeran - (HQ Dreambooth Trained)
![<lora:Ed Sheeran - Trigger is Edsheeran Person:1> Edsheeran person, film footage, a society where people can control the elements, scene from the movie /"Aliens"/, (crying, bawling,:1.3) in a thriller film directed by darren aronofsky , Vitalized and dread, shocked at the power of Artificial Intelligence. Reusable rockets Risk [ Dark|Repetitive behavior|in a new film of a Fantasy world, magical forest, mysterious creatures, Lord of the Rings inspiration. a wizard, standing before a massive ancient tree, speaking to the wind, leaves swirling, ethereal light, hidden figures in the shadowy foliage. Enchanting, mystical, high fantasy, lush and immersive world-building, CGI effects. [Fantasy|magic|forest|wizard|Lord of the Rings]] . Willis Tower (formerly Sears Tower), intricate cinematography, high quality award winning movie footage. Split Lighting](https://go_service.aieasypic.com/?url=https%3A%2F%2Fimage.civitai.com%2FxG1nkqKTMzGDvpLrqFT7WA%2F8929d1ca-5bad-4091-97bd-8f05e960e5fb%2Fwidth%3D450%2F1859182.jpeg&type=webp&width=500&quality=60&civitai=true)
Quick Generate
![<lora:Ed Sheeran - Trigger is Edsheeran Person:1> Edsheeran person, film footage, a society where people can control the elements, scene from the movie /"Aliens"/, (crying, bawling,:1.3) in a thriller film directed by darren aronofsky , Vitalized and dread, shocked at the power of Artificial Intelligence. Reusable rockets Risk [ Dark|Repetitive behavior|in a new film of a Fantasy world, magical forest, mysterious creatures, Lord of the Rings inspiration. a wizard, standing before a massive ancient tree, speaking to the wind, leaves swirling, ethereal light, hidden figures in the shadowy foliage. Enchanting, mystical, high fantasy, lush and immersive world-building, CGI effects. [Fantasy|magic|forest|wizard|Lord of the Rings]] . Willis Tower (formerly Sears Tower), intricate cinematography, high quality award winning movie footage. Split Lighting](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/8929d1ca-5bad-4091-97bd-8f05e960e5fb/width=450/1859182.jpeg)
Model Description by Creator
1.2 - [LoRA version] - Extraction from the Dreambooth trained checkpoint available as Version 1.1
------
High Quality Dreambooth (JP's repo) trained LoRA of musician Ed Sheeran. Created using recent hi-resolution images of the television newscasting star.
Trigger with "Edsheeran Person" (yes, put person also). Use "Hi-Res fix" with the settings you'd normally use for best results. Use prompt weighting and/or Controlnet to get maximum flexibility out of this likeness model.
Trained locally using JP's repo (24gb VRAM req / arguably the best for likenesses). LoRA was extracted directly from the checkpoint trained by Dreambooth available as Version 1 (best possible quality). The A1111 extension "Supermerger" was used to extract/create the LoRA file.
The checkpoint (Version 1) is a clone of what was trained and thus should produce slightly better results. That said in generating samples the LoRA held up really well - so pick the one that makes more sense for your workflow.
Some samples images were generated w/ Controlnet for initial guidance so you won't be able to replicate them with just the metadata (don't think Civitai lists whether or not CN was used).
