FilmPortrait is a LoRA model finetuned on FLUX.1-dev, specifically designed to enhance the film texture. It embodies a subdued, low-saturation color palette reminiscent of classic Japanese cinema, which is particularly evident in its portrayal of characters (with a subtle bias towards Asian features), serene still lifes, and sweeping landscapes. The model delivers an exceptional aesthetic experience, capturing the essence of a bygone era with modern precision.
The following example shows a simple comparison with FLUX.1-dev under the same parameter setting.
1import torch
2from diffusers import FluxPipeline
3
4pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)
5pipe.load_lora_weights('Shakker-Labs/FilmPortrait', weight_name='filmfotos.safetensors')
6pipe.fuse_lora(lora_scale=0.9)
7pipe.to("cuda")
8
9prompt = "a young girl, filmfotos, film grain, reversal film photography"
10
11image = pipe(prompt,
12 num_inference_steps=24,
13 guidance_scale=3.5,
14 width=768, height=1024,
15 ).images[0]
16image.save(f"example.png")
You can also download this model at
Shakker AI, where we provide an online interface to generate images.
This model is trained by our copyrighted users
DynamicWang. We release this model under permissions. The model follows
flux-1-dev-non-commercial-license.
