Prompting as Practice

vibecon 2026 · workshop

prompt engineering for image & video generation
Derrick Schultz · Canyon NYC · June 17–18 2026

I fucking hate prompt engineering

Ultra-realistic vertical photo (9:16).a stylish young man with a lean,toned physique (around 57 kg,5’6 tall) — his beard remains unchanged,and his head is clean-shaven,giving him a modern,confident bald look.He wears one small,silver hoop earring in each ear,adding a subtle yet refined touch of individuality and style.sits on indoor stairs beside a matte concrete wall.A rectangular beam of golden sunlight from a window hits the wall,creating a crisp shadow silhouette inside the bright frame.He wears a black ribbed knit sweater,tapered grey chinos,and chunky white sneakers.Pose: seated,elbows on thighs,hands loosely clasped,chin slightly lifted,eyes looking toward the light,calm and confident expression.Lighting: hard warm sunlight from camera-right as key,soft ambient bounce fill,high contrast with long shadows,cinematic golden-hour mood.Camera & look: low-mid angle from a few steps below,50–85mm f/2.2 lens,shallow depth of field,clean optics,realistic skin texture,fine film grain,subtle vignette.Style: minimalist background,no clutter,fashion editorial realism.Exclude: cartoon,CGI,AI-artifacts,over-smoothing,plastic skin,excessive sharpening,motion blur,warped anatomy,extra fingers,disfigured hands,double shadow,blown highlights,banding,watermark,logo,text,bad perspective,dirty wall,clutter.

I fucking hate can stand prompt
engineering exploring

Derrick Schultz

artist & filmmaker
build custom models on titles.xyz
teach generative AI at NYU
lead creative tech with artists

BBVDAY 2025½

2025 · valentine

A collage film sorted from 18,000+ AI-remixed valentines, cut to Model Man.

structuralist filmmaking by structuring prompts

err me z · 2026

Agentic filmmaking system generates sequences and prompt modifications for stop-motion imagery and video motion.

Phantoms of Endless Day

2025 · LUMA Arles

Ho Tzu Nyen’s four-channel installation at LUMA Arles — built from an algorithmic editing system and 10+ hours of generative AI footage.

training models @ titles

titles.xyz

Trained artist models so anyone can prompt with their work.

The “materiality” of models

Generative particle field — the latent texture of a model

Models have an inherent nature and biases often obscured by humans’ need for “control”.

schedule

01 how prompting works
02 explore
03 expand
04 more to explore

how prompting works

diffusion

how prompting works

The model starts from random noise and refines it, step by step, into an image.

conditioning

how prompting works

Your prompt conditions each step — it biases what the noise resolves into. You don’t draw the image; you steer the denoising.

autoregression

Autoregressive image generation — visual patches predicted one at a time, each conditioned on all previous tokens

how prompting works

Not every model denoises. Autoregressive models build the image one patch at a time — each token predicted from all the ones before, like writing a sentence. Diffusion refines the whole frame at once; autoregression generates it in sequence.

explore

Microscopic bloom of glowing orange and blue filaments

use any site that offers you more than one model

Multi-model generation canvas with model picker and image gallery

where to explore

Titles, Krea, Fuser, Flora, Runway, etc. (Get $5 free when you use titles.xyz 😁)

before we jump to the 200-word prompt, let’s use this time to explore the breadth of these models

no prompt

SDXL

Nano Banana Pro

Seedream 5.0 Lite

explore

Type nothing — on titles, a single comma. See what the model makes from nothing: its raw default.

Note: Nano Banana requires at least 3 characters.

always generate multiple images

explore

Image generation models are non-deterministic. They generate new images every time they are run. Don’t rely on a single output to define the entire model.

Flux Klein 9B Base

a short prompt

SDXL

Flux.1 Dev

Nano Banana Pro

explore

A subject with a style — two or three words is enough to point it somewhere.

expand

Kirlian-style electric glow around a leaf

the basics

Order matters
Some (not all) models support negative prompts — what you don’t want to see

subject: what’s in frame
style: medium & aesthetic
environment: where it sits
lighting: how it’s lit
composition: framing & camera
color: the palette
mood: the overall feeling

Every model prefers of prompts in a specific format.
The right prompt (and the right format) steers the model toward the output you want.

red fox, misty pine forest, dawn, backlit, soft fog, 35mm, shallow depth of field

A lone red fox stands in a misty pine forest at dawn, backlit by soft light through the fog. Shot on 35mm, shallow depth of field.

{
  "subject": "red fox",
  "scene": "misty pine forest",
  "time": "dawn",
  "light": "soft backlight through fog",
  "camera": "35mm, shallow depth of field",
  "mood": "quiet, cinematic",
  "palette": "amber, sage, cool grey"
}

how prompting works

tags — keywords · SD1.5, SDXL
natural language — sentences · Flux, Z-Image, Midjourney
structured data — JSON · Nano Banana, Gemini

most prompting has turned to AI to solve prompt expansion

expand

Today, nearly every AI tool has a “prompt enhancement” feature. Some models even have this built into them so you can’t explore the “raw” model.

one click, many directions

Screenshot — the expand tool’s grid of style/direction icons

expand

Pick a direction instead of writing it all out by hand.

live

the expand tool

prompt-expander-dvsmethid.replit.app

idea in · prompt out

Prompt Workspace — turn a simple idea or image into a detailed generation prompt

Expansion takes your short prompt and rewrites it to match each model’s requirements.

Simple Prompt

“A dog riding a dolphin”

Expanded Prompt

A windswept golden retriever with sand-dusted wet fur and a brass-studded leather harness (#8B5A2B) rides astride a gleaming bottlenose dolphin, both frozen mid-leap over a spray-lashed ocean with the dog’s ears streaming and the dolphin’s skin catching silver-blue specular highlights. Cinematic whimsical adventure in the spirit of Hayao Miyazaki and Steven Spielberg with a rich teal and gold palette using ocean teal #0A6FBF, bioluminescent wake cyan #00E5FF and sunlit gold #FFC857 to heighten wonder and warmth. Lighting is a low hard rim backlight warm golden 3200K coming top-left to carve silhouettes, a cool soft fill at 6500K from camera-right 45° as reflected sky, practical bioluminescent trail lights and volumetric mist rays slicing through spray; shot on a 35mm lens at f/2.8 with shallow depth of field, 1/500s to freeze motion, subtle 35mm anamorphic horizontal flares and fine film grain for tactile, film-quality texture.

add styles

expand

Lighting, lens, mood, composition — added for you, without writing it all out.

structured data

Skip it for quick exploration — it’s verbose and slows you down
Only some models truly parse it (Nano Banana, Gemini); most diffusion models (SDXL, Flux) just read it as plain text

Use JSON when you want precise, repeatable control — one field per attribute.
Change one field, hold the rest constant.

expand to JSON

expand

Structured, repeatable prompts — change one field, hold the rest constant.

more to explore

$Soft coral-like fractal bloom$

image → prompt

Image-to-prompt tool — upload an image, get an extracted prompt, regenerate

bonus

Upload an image; a VLM extracts a base prompt you can edit, then regenerate.

inversion

the prompt a VLM extracted from this image

Hyperrealistic close-up of a vibrant orange goldfish and a smaller companion in a square glass aquarium, lush green seaweed and mossy gravel around a single smooth stone, tiny rising bubbles and subtle glass reflections against a deep, nearly black backdrop. Centered tight composition with high-value contrast and soft cinematic rim lighting, crisp fine-detail linework and airbrushed shading for velvety scales and glass highlights, saturated warm oranges against cool deep greens in a National Geographic-style macro photography aesthetic.

pipeline

image → VLM (“describe as a prompt for this model”) → base model → generate → compare → revise the query.

failure mode

VLMs default to content — “a woman in a red coat.”
You often want style — “grainy 35mm, blown highlights, teal shadows.”
Specify which to extract.

constrain the VLM

“describe only lighting and color.”
“ignore the subject; capture rendering style.”
“output as sdxl tags.”

The VLM’s output is controllable — constrain it.

live demo

image → prompt → image

prompt-expander-dvsmethid.replit.app

image in · formatted prompt out · regenerate

applications

• reproduce a target look
• maintain one style across many images
• convert a film still into a generatable prompt

image edit prompts

Input image — felted corgi riding a dolphin

Edited result — the dog swapped to a St. Bernard, everything else held

more to explore

Image-edit models take an existing image plus a text instruction. Same scene, same style — only the dog’s breed changed.

image edit

popular edit models

Nano Banana · Flux Kontext · Qwen Edit · Seedream · GPT-Image

target the change: edit, don’t redescribe the scene
preserve: name what stays — identity, pose, background
be concrete: “the dog,” not “it”
place it: left, right, foreground, behind
match the light: keep direction, softness, color temp
exclude: say what you don’t want — no added objects, no text

video prompts

more to explore

Now you direct motion and camera — not just the frame, but what happens over time.

text → video

If you still hate prompting…

train a model with Titles

Custom model output — dog riding a dolphin

more to explore

Bake a style or subject into the model so you barely have to describe it.

train a model with Titles

more to explore

One model, one subject — endlessly re-promptable.

thanks

find me