Ultimate Cinematic Prompt Studio

🎬 Ultimate Cinematic Prompt Studio – ComfyUI Workflow

Created by Me – a filmmaker & AI workflow designer. This is the ultimate all‑in‑one cinematic image generation studio. It combines camera controls, lighting design, character creation, action/emotion, scene elements, style selection, framing, landscape generation, and even a Prompt Randomizer that randomises everything with one click. No more messy node spaghetti – just select, toggle, randomise, and generate stunning cinematic images.

🧩 Overview

This workflow is designed to be the complete creative suite for image generation. It includes:

• Cinematic Aspect Ratio Selector – 10+ standard and cinematic ratios (HD, Anamorphic, Square, etc.) with quality scaling.

• Camera Selector – angle, shot size, position, lens.

• Camera Movement Selector – movement type, turn, shake, speed.

• Light Selector – environment, time of day, weather, light type, colour, direction, quality, contrast, Kelvin, genre.

• Landscape Prompt Generator – landscape type, mood, vegetation, sky element.

• Character Generator – gender, age, clothing, texture, decade.

• Action Generator – action, expression, orientation.

• Scene Element Generator – foreground, midground, close elements, across‑frame elements.

• Style Selector – style, medium, colour tone, detail, nationality.

• Framing Selector – Over‑the‑Shoulder, Dutch, etc.

• Model Loader with LoRAs – load diffusion model, CLIP, VAE, and up to 5 LoRAs with trigger words.

• Image Generator – combines everything and outputs a high‑quality image.

• Save Image Custom – save with date, size, seed, custom folder, and project name.

• Prompt Randomizer – randomise camera, movement, light, landscape, character, action, scene elements, style, and framing – all with one click.

All nodes are custom‑built by me for cinematic workflows – and they're fully modular, so you can use any model you like.

1️⃣ Required Models & Prerequisites

Make sure these files are placed in your ComfyUI models/ folders:

FolderRequired Filesdiffusion_models/Any model you prefer (e.g., krea2_turbo_fp8_scaled.safetensors, qwen_image_2512_fp8_e4m3fn.safetensors, etc.)text_encoders/The CLIP model matching your diffusion model (e.g., qwen3vl_4b_fp8_scaled.safetensors, qwen_2.5_vl_7b_fp8_scaled.safetensors, etc.)vae/qwen_image_vae.safetensors (or your preferred VAE)loras/Your custom LoRAs (optional – up to 5 can be loaded)

⚠️ Installation Required: This workflow uses my custom nodes. You must install (or update) ComfyUI-Saeed-Nodes first:

bash

git clone https://github.com/saeedkhalili/ComfyUI-Saeed-Nodes

Place the cloned folder inside your ComfyUI custom_nodes/ directory and restart ComfyUI.
If you already have it installed, please pull the latest updates – this workflow uses new nodes not available in older versions.

💡 Flexible Engine: This workflow works with any diffusion model (Krea, Qwen, Flux, SDXL, Z‑Image, etc.). Just select your model files in the ModelLoaderWithLora node and adjust the CLIP type accordingly.

3️⃣ How It Works (One‑Click Cinematic Generation)

1. Select aspect ratio – choose your desired frame.

2. Set camera parameters – angle, shot size, position, lens, movement, shake, speed.

3. Design lighting – environment, time, weather, light type, colour, direction, quality, contrast, Kelvin, genre.

4. Build your scene – choose landscape, characters, action/emotion, scene elements, style, and framing.

5. Load your model & LoRAs – pick your diffusion model, CLIP, VAE, and up to 5 LoRAs.

6. Randomise everything (optional) – click the Prompt Randomizer to instantly randomise all creative choices with one click.

7. Generate image – the Image Generator combines all prompts and produces a high‑quality image.

8. Save with style – SaveImageCustom lets you save with date, size, seed, custom folder, and project name.

All custom nodes are designed for simplicity – just select, toggle, randomise, and generate!

6️⃣ Advanced Settings (Optional)

• LoRA Trigger Words – each LoRA can have its own trigger word, automatically added to the prompt.

• Quality K – adjust quality scaling in the aspect ratio selector for faster or higher‑quality latents.

• Aura Flow Shift – fine‑tune model sampling shift (adjustable per model).

• Negative Prompt Toggles – quickly disable unwanted elements without typing long negatives.

• Custom Negative Words – add your own negative terms.

• Seed, Steps, CFG, Sampler, Scheduler – full control over KSampler parameters.

• Save Customisation – SaveImageCustom lets you include size, date, seed, and custom folder/project name in filenames.

• Prompt Randomizer – randomise camera, movement, light, landscape, character, action, scene elements, style, and framing with one click – perfect for creative exploration and inspiration.

📦 Final Output

After running, you'll get a high‑quality cinematic image saved with a descriptive filename that includes your project name, ratio, date, size, and seed – all organised automatically.

Why I built this: As a filmmaker, I needed a single, clean workflow that could generate consistent, high‑quality images without dragging dozens of nodes around. I wanted everything – camera, lighting, characters, action, style, framing – all in one place, with the ability to randomise everything for creative exploration. These custom nodes let me focus on creativity while the AI handles the rest. And because you can swap the engine and LoRAs, it works with whatever model you love. Perfect for storyboarding, concept art, background generation, or just exploring cinematic ideas. I hope it helps you create stunning images as easily as I do! 🌄🎥

📬 Contact: If you’d like to donate, ask a question, or order a custom workflow, reach out to me on Civitai (SaeedKhalili), visit my website SaeedKhalili.com, or email me at [email protected]. I’m always happy to help fellow creators!