Skip to content
WorkflowListedExternal
Open source

Random photorealistic prompt — v1.0

This was inspired by PromptGeek's YouTube video and eBook so all credits goes to them. Please go and show them some love: Creating Photorealistic Images With AI: Using Stable Diffusion

Sourcecivitai.com/models/2375856
FamilyStable DiffusionVersionRelease 2671862 — Random Photorealistic Image.jsonEstimated VRAMNot yet characterizedBgrade

Runtime profile

Access
External workflow
Status
Listed
Version
Random Photorealistic Image.json
Source
Civitai
Updated
Sep 30, 2026

Source description

This was inspired by PromptGeek's YouTube video and eBook so all credits goes to them. Please go and show them some love: Creating Photorealistic Images With AI: Using Stable Diffusion

This workflow builds a random prompt with keywords from the eBook mentioned above following this pattern (also from the eBook): [STYLE OF PHOTO] photo of a [SUBJECT], [IMPORTANT FEATURE], [MORE DETAILS], [POSE OR ACTION], [FRAMING], [SETTING/BACKGROUND], [LIGHTING], [CAMERA ANGLE], [CAMERA PROPERTIES],in style of [PHOTOGRAPHER]

In the "Inputs here" group, you set a seed, select a checkpoint and image size. To the right, you set your subject, and optionally a negative prompt. The generated positive prompt can be seen in the console.

In the "Random parameters" group, you can add and remove keywords. You may also want to edit the output path.

I use two custom node packs. The first one, was-node-suite-comfyui, is a must. It's apparently retired but works fine: https://github.com/WASasquatch/was-node-suite-comfyui

The other one, cg-use-everywhere, just keeps things neat. You can connect seed, model, clip, vae, and latent manually if you don't want to install it: https://github.com/chrisgoringe/cg-use-everywhere

Have fun.

What you need

Hardware and download-size estimates are not available yet.

Requirements

Models

1

AI-generated commentary

AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.

Purpose

  • Use this workflow to build a randomized photo prompt from a subject and keyword choices; set a seed, checkpoint, and image size, optionally add a negative prompt, and read the generated positive prompt in the console.

Flow

  • The prompt can combine photo style, subject, features, details, pose or action, framing, setting, lighting, camera angle and properties, and photographer.

Inputs and outputs

  • Set the seed, checkpoint, and image size in “Inputs here”; enter a subject and optional negative prompt in the adjacent fields.

  • The positive prompt appears in the console, and the output path is editable.

Setup

  • The author lists was-node-suite-comfyui as required.

  • cg-use-everywhere is optional; you can connect seed, model, CLIP, VAE, and latent manually instead.

Dependencies

  • The workflow names juggernautXL_v8Rundiffusion.safetensors as a checkpoint.

Configuration

  • In “Random parameters,” add or remove keywords to change the prompt choices; edit the output path if needed.

Cautions

  • The author describes was-node-suite-comfyui as apparently retired, so check its current availability before setup.

    Suggestion · not verified

Does this need to be edited?

Sign in to send an edit request.

Sources

1 source
CivitaiSourceVersion 2671862
civitai.com/models/2375856

Verified Sep 30

Source excerpts

3 excerpts
NoteSep 29civitai.com/models/2375856

Source context: 86 downloads · Type Workflows · Base model SDXL 1.0

NoteSep 28civitai.com/models/2375856

Source context: 85 downloads · Type Workflows · Base model SDXL 1.0

NoteJul 18civitai.com/models/2375856

Source context: 70 downloads · Type Workflows · Base model SDXL 1.0