[Stable Diffusion] A selfie in nature

This is the whole configuration:

• Prompt: RAW photo, beautiful landscape, (selfie:1.1), 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3,
• Negative prompt: (deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime), text, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck, BadDream, asian
• Steps: 30
• Sampler: DPM++ SDE Karras
• CFG scale: 7
• Seed: 3082747622
• Size: 512x512
• Model hash: ef76aa2332
• Model: realisticVisionV51_v51VAE
• VAE hash: c6a580b13a
• VAE: realisticVisionV51_v51VAE-inpainting.vae.pt
• Denoising strength: 0.45
• Hires upscale: 2
• Hires steps: 10
• Hires upscaler: 4x-UltraSharp
• Lora hashes: "add_detail: 7c6bad76eb54"
• Version: v1.6.0

Basically I use the settings above. This time I added asian to the negative prompt, but other than that I use the exact some negative prompt every time with this model (with some minor modifications as I need them).

For the prompt I do this: RAW photo, *insert subject here*, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3, - I replace the *insert subject here* with the subject I want, in this case it's beautiful landscape, (selfie:1.1).

The upscale settings are not necessary, though they obviously make the image look better when it's viewed up-close.

Links:

• model: https://civitai.com/models/4201/realistic-vision-v51
• add detail lora: https://civitai.com/models/58390/detail-tweaker-lora-lora
• VAE: https://huggingface.co/stabilityai/sd-vae-ft-mse-original

Let me know if anything's unclear!