Turns any scene into a real-looking Polaroid instant photo: white frame with the wide bottom border, faded warm colors, soft shadows, flash glare and that slightly imperfect chemical look.Works on portraits, nightlife flash shots, travel, food, cars, interiors. It doesn't care about the subject, only the look.HOW TO USETrigger word: p0laroidStart your prompt like this:p0laroid, a polaroid instant photo, &lt;your scene&gt;Recommended settings• LoRA weight: 1.0 (0.8 if faces start to drift)• Size: 896×1088 (true Polaroid proportions with the frame). Square works too, but the frame shows up less often.• 25 steps, CFG 2.5, er_sde / simple• If the frame disappears, add to the end: white polaroid border with a wider bottom edge• Avoid the words "frame" / "cropped" in the scene description. The model reads them as "camera frame" and drops the border.All preview images were made locally in ComfyUI with the official MOSS-Image SFT int8 template + this LoRA. Prompts are in the image metadata.Also available for Qwen Image 2.1. Look for "Polaroid Instant Film | Qwen Image 2.1" on my profile.<h3 id="more-workflows-loras-and-guides:-seedraai.com">More workflows, LoRAs and guides: <a target="_blank" rel="ugc" href="http://seedraai.com">seedraai.com</a></h3>DATASET &amp; CREDITSTrained on 54 real Polaroid photos from Wikimedia Commons, all under free licenses (CC BY / CC BY-SA). Huge thanks to the photographers:Sasha Kargaltsev, Makia Minich, Johan Hansson, C. J. Lee, Kevin Dooley, Tom Hart, Moki8, <a target="_blank" rel="ugc" href="http://Yellow.Cat">Yellow.Cat</a>, Peter Pawlowski, Tony Webster, Sgroey, Academicien, Mrnerd1billion, Nick McManus, Minimalist100.Licenses: CC BY 2.0, CC BY 3.0, CC BY 4.0, CC BY-SA 3.0, CC BY-SA 4.0.

SEEDRAAI | Polaroid Instant Film | MOSS Image

First release. Trained on MOSS Image SFT, 54 real Polaroid photos, 3000 steps. Best at 896×1088, weight 1.0, 25 steps, CFG 2.5, er_sde / simple.

p0laroid_moss_v1.safetensors

v1.0


# 

## Model Introduction

This model is trained using the [Civision/model training](https://modelscope.ai/civision/modelTraining) environment and computing resources provided by ModelScope.

* Model Type: LoRA
* Base Model: [openmoss/MOSS-Image-SFT](https://modelscope.ai/models/openmoss/MOSS-Image-SFT)
* Training Code: [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio)
* Data amount：54
* Total training steps：3000
* License: Apache-2.0

## Inference Code

Install [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio):

```bash
pip install diffsynth
```

Inference:

```python
from diffsynth.pipelines.moss_image import MOSSImagePipeline, ModelConfig
import torch

pipe = MOSSImagePipeline.from_pretrained(
    torch_dtype=torch.bfloat16,
    device="cuda",
    model_configs=[
        ModelConfig(model_id="openmoss/MOSS-Image-SFT", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors"),
        ModelConfig(model_id="openmoss/MOSS-Image-SFT", origin_file_pattern="text_encoder/model*.safetensors"),
        ModelConfig(model_id="openmoss/MOSS-Image-SFT", origin_file_pattern="vae/diffusion_pytorch_model.safetensors", computation_dtype=torch.float32),
    ],
    tokenizer_config=ModelConfig(model_id="openmoss/MOSS-Image-SFT", origin_file_pattern="tokenizer/"),
)
pipe.load_lora(pipe.dit, ModelConfig(model_id="cfgscale/p0laroid_moss_v1", origin_file_pattern="p0laroid_moss_v1_c1-st3000.safetensors"))

prompt = "a cat"
image = pipe(prompt, height=1024, width=1024, seed=0, num_inference_steps=50, cfg_scale=3.0)
image.save("image.jpg")
```


Files with SHA256: 8812c50cbd5643a68e72758a86b1dda2e52d44b9f7a722e38f547b7deeaaa96e