Stable Diffusion Prompt Guide

There is not a single model that can generate a correct flintlock rifle with realistic hand pose so i guess i will have to do a lora for it.

I don't subscribe very often, but for you, oh yea! Fantastic information! Thank you.

Thank you very much for this immense help... the part where you talk about the order in the prompt, I tested it by changing things around to match this structure and it made a big difference...

These terms are widely recognized and effective across different diffusion models, including SD, SDXL, and Flux, ensuring consistency and high-quality results in your generations!

General Quality Enhancers:
High quality, highly detailed, ultra-detailed, photorealistic, 4K, 8K, UHD, sharp focus, crystal clear, hyper-realistic, vivid colors, exceptional quality, enhanced textures, precise rendering, finely detailed, professional rendering, masterpiece, award-winning,

General Style Enhancers:
Digital art, concept art, matte painting, anime style, oil painting, watercolor, pencil sketch, ink drawing, modern illustration, fantasy art, sci-fi concept art, vaporwave, synthwave, pixel art, cyberpunk, steampunk, gothic art, abstract art, minimalistic, maximalist, retro comic style, light academia, dark academia,

General Lighting & Atmosphere:
Ambient lighting, soft lighting, dramatic shadows, backlit, volumetric lighting, cinematic lighting, atmospheric, ethereal, glowing, luminescent, moody, melancholic, golden hour, neon lighting, twilight, misty, foggy, high contrast, low contrast, dreamy lighting,

General Composition & Focus:
Centered composition, rule of thirds, symmetrical, asymmetrical, close-up, wide-angle shot, dynamic pose, depth of field, bokeh effect, panoramic, macro shot, mid-shot, bird's-eye view, focal point emphasis, blurred background, leading lines, dynamic composition,

General Time & Style Periods:
80s style, retro-futuristic, cyberpunk, Victorian era, modern aesthetic, vintage, classic, medieval, baroque, Renaissance, futuristic, dystopian, utopian, Art Deco, contemporary, rustic, industrial, steampunk,

General Emotion & Theme:
Melancholic, whimsical, nostalgic, romantic, epic, heroic, surreal, dreamlike, dark, mysterious, serene, joyful, eerie, haunting, tranquil, hopeful, suspenseful, dramatic, inspiring, bittersweet, playful, adventurous, contemplative, otherworldly,

General Technical Terms:
CGI, VFX, Octane render, Unreal Engine, ray tracing, high dynamic range (HDR), PBR (Physically Based Rendering), procedural generation, motion blur, depth map, texture mapping, 3D render, ambient occlusion, global illumination, shader, voxel, subsurface scattering,

I just wanna say that you're amazing, man

great explanation and good tips, thank you so much. i can just copy what is said above: no bullshit, no ads, no intro, just straight to the point

Great video I’m new to stable diffusion and never used a lot of those options!

Great video mate! Super informative, and straight to the point!

Excellent video. Glad I watched it. Liked and Subbed.

❤👌🏻

Just wow, I cannot stop watching 💣

Good video, found this all out the hard way lol
subscribed.

Nice video! Why is it so difficult to find any tutorial that shows how to use Stable Diffusion to add text to an existing image? Can you help?

After a long search finally an amazing video.

hey mate, what specs in pc you have? e.g GPU

Great, helpful video, thank you.

Thank you for the video, quick question: when I try to create an x/y/z script to generate multiple photos like you, for example with different STEPs, I do get several photos generated, but I don’t have the captions to identify which photo contains which setting. Also, at the end, I don’t see all the photos lined up for comparison at a glance. I only see one photo, and I have to go into my folder to see the others. However, I have enabled "draw legend." Is there something I need to adjust in the settings? Thank you very much for your help.

Example of one of my prompts:
Cinematic photo of a Celtic woman, with pale skin, fiery red hair cascading over her shoulders, and bright blue eyes. She wears a woolen cloak fastened with a bronze brooch and is adorned with silver bracelets. Behind her, misty forests and ancient standing stones rise in the background, ultra realistic, Shot with a Nikon F3 and a 35mm ƒ2 lens, using Kodak Portra 400 film stock

I'm having difficulty getting two subjects to interact. As an example I want two characters to simply "shake hands" well what ensues instead is a disembodied horror show. Advice?

this might just be one of the best videos ive learned from thank you.

Love these videos

Wow wow wow. Fantastic video that doesnt have a goofy voice and those quickly paced captions. Thanks!!

Awesome video, liked

to generate the images quicker to i need a better GPU CPU RAM ?

Very good!

ooo k ay ! Next step, making Weird Science with this thumbnail o0

great video. Wish I had found you months ago, it would have saved me a lot of time. Liked and subscribed.

how is ur generation so fast lol, if i dare go over 612x612 it just stops and dies. even with lower end models.

FROG! I've been using SD like google search no wonder I always get crappy result... Its actually opposite of google search.... Sheesh!

This is a Goody 💪💪

Very informative and no nonsense. Subbed and liked!

Thank you so much for sharing. Your tutorial series are greatly helpful for the starters.

What voice software did you use in making this video?

Hands and feet *smdh*, hands and feet.

very good video, thanks a lot this is a gold mine

Good video thanks for the information

Create discord server, no one uses facebook these days. (atleast i dont).
With midjourney and games seeing a rise, i am confident the upcoming generation has discord account.

love it, learned a lot of new tricks. What are your specs you are running, GPU, Processor, Ram ?? yours generates pretty fast.

Finally a pro. No bs, no intro, straight to the point. Subscribed

hmmmm uniforms...

great vid...what causes anatomical mutations and how to address this formidable non-intelligent conundrum,

how come your stavle diffusion like a trained dog, as i have everyting same but never get what i want

Could you make a complete guide/tutorial about "Regional Prompter" extension for AUTO and how to get 2 characters interacting? Thx in advance.

@pixaroma

Once again, you knocked it out of the park. You are in the major leagues. :)

Thank's a lot 💚💚💚

Thanks!!