SD3.5-Large-Photorealistic-LoRA

Prompt
A photorealistic portrait of a young woman with short dark brown hair, wearing a grey spaghetti-strap top, standing outdoors in soft daylight. The background includes a blurred pool and greenery, creating a serene and summery atmosphere. Warm lighting highlights her natural beauty and relaxed expression.
Prompt
Man in the style of dark beige and brown, uhd image, youthful protagonists, nonrepresentational photography
Prompt
Black and white photography in style by Bruce Davidson, fashion editorial, dark haired woman of long exposure photography through artistic lens, highres, realistic photo, professional photography, cinematic angle, dynamic light back shining, bokeh

The model is still in the training phase. This is not the final version and may contain artifacts and perform poorly in some cases.

Model description

prithivMLmods/SD3.5-Large-Photorealistic-LoRA

Image Processing Parameters

Parameter Value Parameter Value
LR Scheduler constant Noise Offset 0.03
Optimizer AdamW Multires Noise Discount 0.1
Network Dim 64 Multires Noise Iterations 10
Network Alpha 32 Repeat & Steps 20 & 1.5K
Epoch 10 Save Every N Epochs 1
Labeling: florence2-en(natural language & English)

Total Images Used for Training : 40

Setting up

import torch
from diffusers import StableDiffusion3Pipeline

pipe = StableDiffusion3Pipeline.from_pretrained("stabilityai/stable-diffusion-3.5-large", torch_dtype=torch.bfloat16)
pipe.load_lora_weights("prithivMLmods/SD3.5-Large-Photorealistic-LoRA", weight_name="Photorealistic-SD3.5-Large-LoRA.safetensors")
pipe.fuse_lora(lora_scale=1.0)
pipe.to("cuda")

prompt = "Man in the style of dark beige and brown, uhd image, youthful protagonists, nonrepresentational photography"
negative_prompt = "(lowres, low quality, worst quality)"

image = pipe(prompt=prompt,
             negative_prompt=negative_prompt
             num_inference_steps=24, 
             guidance_scale=4.0,
             width=960, height=1280,
            ).images[0]
image.save(f"example.jpg")

Trigger words 🧨

You should use photorealistic to trigger the image generation.

You should use photography to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.

Downloads last month
3,990
Inference API
Examples

Model tree for prithivMLmods/SD3.5-Large-Photorealistic-LoRA

Adapter
(174)
this model

Spaces using prithivMLmods/SD3.5-Large-Photorealistic-LoRA 4

Collection including prithivMLmods/SD3.5-Large-Photorealistic-LoRA