Type | |
Stats | 325 27 |
Reviews | (49) |
Published | Jan 6, 2025 |
Base Model | |
Training | Steps: 3,000 Epochs: 6 |
Usage Tips | Clip Skip: 2 Strength: 0.9 |
Trigger Words | SoftLight effect film grain |
Hash | AutoV2 AF657A1E82 |
《Film photography》
This series of LoRA aims to restore various Asian photography styles. Through learning the style preferences in multiple details such as the color, focal length, and exposure of photography works, it can simulate the beautiful moments in the photographer's eyes relatively well, eliminate the problem of overly shiny skin in the FLUX model to the greatest extent, reduce the texture of artificial intelligence, and the output is closer to real photography.
When using this series of Lora, it is recommended to start with a weight of 0.9. The following are the specific recommended parameters.
Recommended weight: 0.9 - 1.5
Recommended size: 768/1024/1536.
Guidance condition: 2.0 - 3.0
Steps: 20 - 40
Sampler: euler/dpm++
To achieve the best output effect, it is recommended to be paired with the exclusive workflow
OK, that's all
If you enjoy my work, please give me a "like" rating; it means a lot to me!If you enjoy my work, please give me a "like" rating; it means a lot to me!If you enjoy my work, please give me a "like" rating; it means a lot to me!
Check out other creations here
Thank you for reading up to here. English is not my native language. The above is translated by AI. If there is anything inappropriate, welcome to correct me. Thank you.