rh-candid-snapshot-realism-lora
Description
| Field | Content |
|---|---|
| Model Name | rh-candid-snapshot-realism-lora |
| Model Type | LoRA (image edit) |
| Platforms | ComfyUI / RunningHub / Hugging Face |
| Author | RunningHub-@氛围感 |
| Original | https://www.runninghub.ai/model/public/2079002853636673537 |
| Try online | https://www.runninghub.ai |
| https://www.runninghub.cn/runninghub-api-doc-en/ |
About this model
Original URL: https://civitai.red/models/2790570/krea2-raw-casual-snapshot-realism?modelVersionId=3144693
Tired of overly plastic, polished, and stylized "perfect AI" photos? This LoRA is built for your generation, designed to inject authentic, natural smartphone photography character. Based on the Krea-2 RAW base model, it is natively trained on high-resolution, naturally annotated amateur snapshots, perfectly capturing the subtle textures and imperfections of everyday mobile shooting.
Key Aesthetic Features
Realistic Camera Imperfections: Captures natural low-light digital noise, sensor grain, soft-focus highlights, and lens smudges.
Authentic Lighting Behavior: Natively handles tricky lighting scenarios such as harsh indoor flashes, mixed ambient light, and natural backlit lens flares (ideal for window shots and mirror selfies).
Candid Composition: Excels at capturing natural, spontaneous poses, mirror reflections, and everyday street photography without looking forced or like studio-lit photos.
How to Use My Recommended Resources (Below)
To get results identical to those shown in the preview images, please use the resources linked at the bottom of this page:
Base Model: Load Krea 2 Raw for the most raw photographic detail and grain.
Workflow: For the best ComfyUI settings, get the PhotoFlow workflow from the attachments below.
Fast Execution: If you want to run quick multi-step iterations, you can stack this model with the connected Krea 2 Turbo LoRA.
Generation Guide
Core Parameters
Trigger Word:
r3alismLoRA Weight: (Start with
1.0 - 1.25, use1.0for a perfect balance of texture and flexibility).
Prompt Strategy
This LoRA system relies on natural language descriptive paragraphs rather than simple tag lists. Explicitly describe the flaws of the camera environment to guide the output:
Indoor Snapshot:
r3alism, a casual flash mirror selfie of a woman in her bedroom, messy hair, low-light phone camera texture...Outdoor Night Shot:
r3alism, an amateur smartphone snapshot of a person walking on a city street at night, visible digital noise, yellow streetlamp glow...
Recommended Settings
This repository provides rh-candid-snapshot-realism-lora weight files. You can load them on RunningHub.
Finetuned from: krea2
Trigger words: 现实主义
Files
| File | Size | Purpose |
|---|---|---|
krea2-s3lfie-r3alism-9.safetensors |
448 MiB | LoRA weights |
License
Published by RunningHub on behalf of the author. Copyright remains with the author. Follow the original project or upstream license.
Training at RunningHub
Train models on RunningHub: https://www.runninghub.ai/page-model
Run Seedance 2.5 with RunningHub API: https://www.runninghub.ai/call-api/api-detail/2133100000000700025
- RunningHub：https://www.runninghub.ai
- RunningHub 中国站：https://www.runninghub.cn
- RunningHub API 文档：https://www.runninghub.cn/runninghub-api-doc-cn/
- RunningHub API Documentation：https://www.runninghub.cn/runninghub-api-doc-en/
- Original project: https://www.runninghub.ai/model/public/2079002853636673537
- Author page: https://www.runninghub.ai/user-center/2041030036219498497