Prompting

Prompts describes what a model should generate. Good prompts are detailed, specific, and structured and they generate better images and videos.

This guide shows you how to write effective prompts and introduces techniques that make them stronger.

Writing good prompts

Every effective prompt needs three core elements.

1. Subject - what you want to generate. Start your prompt here.
2. Style - the medium or aesthetic. How should it look?
3. Context - details about actions, setting, and mood.

Use these elements as a structured narrative, not a keyword list. Modern models understand language better than keyword matching. Start simple, then add details.

Context is especially important for creating better prompts. Try adding lighting, artistic details, and mood.

Be specific and add context. Use photography terms like lens type, focal length, camera angles, and depth of field.

Try a prompt enhancer to help improve your prompt structure.

Prompt weighting

Prompt weighting makes some words stronger and others weaker. It scales attention scores so you control how much influence each concept has.

Diffusers handles this through prompt_embeds and pooled_prompt_embeds arguments which take scaled text embedding vectors. Use the sd_embed library to generate these embeddings. It also supports longer prompts.

The sd_embed library only supports Stable Diffusion, Stable Diffusion XL, Stable Diffusion 3, Stable Cascade, and Flux. Prompt weighting doesn’t necessarily help for newer models like Flux which already has very good prompt adherence.

!uv pip install git+https://github.com/xhinker/sd_embed.git@main

Format weighted text with numerical multipliers or parentheses. More parentheses mean stronger weighting.

Create a weighted prompt and pass it to get_weighted_text_embeddings_sdxl to generate embeddings.

You could also pass negative prompts to negative_prompt_embeds and negative_pooled_prompt_embeds.

import torch
from diffusers import DiffusionPipeline
from sd_embed.embedding_funcs import get_weighted_text_embeddings_sdxl

pipeline = DiffusionPipeline.from_pretrained(
    "Lykon/dreamshaper-xl-1-0", torch_dtype=torch.bfloat16, device_map="cuda"
)

prompt = """
A (cute cat:1.4) lounges on a (floating leaf:1.2) in a (sparkling pool:1.1) during a peaceful summer afternoon.
Gentle ripples reflect pastel skies, while (sunlight:1.1) casts soft highlights. The illustration is smooth and polished
with elegant, sketchy lines and subtle gradients, evoking a ((whimsical, nostalgic, dreamy lofi atmosphere:2.0)), 
(anime-inspired:1.6), calming, comforting, and visually serene.
"""

prompt_embeds, _, pooled_prompt_embeds, *_ = get_weighted_text_embeddings_sdxl(pipeline, prompt=prompt)

Pass the embeddings to prompt_embeds and pooled_prompt_embeds to generate your image.

image = pipeline(prompt_embeds=prompt_embeds, pooled_prompt_embeds=pooled_prompt_embeds).images[0]

Prompt weighting works with Textual inversion and DreamBooth adapters too.