Amateur Selfies v2
Back

Amateur Selfies v2
71 0 4

Stylization

Amateur Selfies v2

https://civitai.com/models/1969289?modelVersionId=2279752


Amateur Selfies is a LoRA trained on ~1000 casual self-portrait photos, designed to capture the look, feel, and imperfections of real-world selfies. It emphasizes natural framing, handheld angles, everyday environments, and the aesthetics of self shot phone photographs.

Recommended settings after more experimentation

  • LoRA strength: 0.9 - 1.0. I accidentally generated the 'redux' showcase images with 0.9 and they're fine.

  • FP8 or BF16 UNET. GGUF quants cause checkboard artifacts, do not recommend! FP8 can actually 'enhance' the amateur look

  • 50 steps

  • CFG 3.0

  • euler/beta

  • <= 2.0 MP

Workflow is included in the sample images.

I have identified a couple of issues with training captions and masks:

  • captions were natural language formatted in paragraphs. The newline paragraph separators however are interpreted by SimpleTuner as delimiter for individual captions.

  • masks weren't applied due to a derp in the dataset config

I'm working on training v2.0 now using the same image set, but with new captions and fixed masks (face removal). Also appending some quality captions which should improve the sharpness of outputs when not prompting specifically for poor quality / compression artifacts.

This model is sourced from an external transfer (transfer address: https://civitai.com/models/1969289?modelVersionId=2279752 ）,if the original author has objections to this transfer, you can click，
Appeal
We will, within 24 hours, edit, delete, or transfer the model to the original author according to the original author's request

user_h4r8bfxd

user_h4r8bfxd

Stylization

Model Information

Frozen
Original author：
psychologicau
Model Type：
LoRA
Basic Model：
Qwen-image
Resource Name：
models/loras/AmateurSelfie_v2.safetensors
MD5：
b7b01ed5eb00d4165de4ad833bfdbb4c

https://civitai.com/models/1969289?modelVersionId=2279752


Amateur Selfies is a LoRA trained on ~1000 casual self-portrait photos, designed to capture the look, feel, and imperfections of real-world selfies. It emphasizes natural framing, handheld angles, everyday environments, and the aesthetics of self shot phone photographs.

Recommended settings after more experimentation

  • LoRA strength: 0.9 - 1.0. I accidentally generated the 'redux' showcase images with 0.9 and they're fine.

  • FP8 or BF16 UNET. GGUF quants cause checkboard artifacts, do not recommend! FP8 can actually 'enhance' the amateur look

  • 50 steps

  • CFG 3.0

  • euler/beta

  • <= 2.0 MP

Workflow is included in the sample images.

I have identified a couple of issues with training captions and masks:

  • captions were natural language formatted in paragraphs. The newline paragraph separators however are interpreted by SimpleTuner as delimiter for individual captions.

  • masks weren't applied due to a derp in the dataset config

I'm working on training v2.0 now using the same image set, but with new captions and fixed masks (face removal). Also appending some quality captions which should improve the sharpness of outputs when not prompting specifically for poor quality / compression artifacts.

This model is sourced from an external transfer (transfer address: https://civitai.com/models/1969289?modelVersionId=2279752 ）,if the original author has objections to this transfer, you can click，
Appeal
We will, within 24 hours, edit, delete, or transfer the model to the original author according to the original author's request