# Cinematic Image Generator Workflow for ComfyUI
Create stunning, cinematic images with just a few clicks – no need to manually type complex camera or lighting prompts.
This workflow combines five powerful custom nodes (from the ComfyUI-Saeed-Nodes pack) to give you full control over aspect ratio, camera angle, lighting, and model loading, all in one clean setup.
---
## 🚀 What You Get
- One‑click cinematic presets – camera angle, shot size, lens, movement, and even handheld shake.
- Professional lighting control – indoor/outdoor, time of day, weather, light type, colour, contrast, and genre.
- Aspect ratio selector – pick a cinematic ratio and let the node create the correct latent.
- Model & LoRA loader – load your diffusion model, CLIP, VAE, and up to 5 LoRAs in a single node.
- Final image generator – merges all prompts, optionally applies AuraFlow, and outputs the final image with a smart filename.
Everything is pre‑wired, so you can start generating high‑quality images immediately.
---
## 📦 How to Install the Required Custom Nodes
The workflow uses ComfyUI-Saeed-Nodes.
Install it manually or via ComfyUI Manager.
### Option 1 – ComfyUI Manager (easiest)
- Open ComfyUI, go to Manager → Install via Git URL.
- Paste: https://github.com/saeedkhalili/ComfyUI-Saeed-Nodes
- Restart ComfyUI.
### Option 2 – Manual Installation
- Download the ZIP from [GitHub](https://github.com/saeedkhalili/ComfyUI-Saeed-Nodes) or clone the repository.
- Place the ComfyUI-Saeed-Nodes folder into your ComfyUI/custom_nodes/ directory.
- Restart ComfyUI.
After restart, you’ll find the new nodes under the Saeed category.
---
## 🧠 Recommended Models (what I use for realistic, high‑quality images)
These are the exact models I use with this workflow. All are free and widely available.
| Model | Type | Source |
|-------|------|--------|
| Qwen Image 2512 (FP8) | Diffusion Model | [HuggingFace – Comfy‑Org/Qwen‑Image](https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/tree/main/split_files/diffusion_models) |
| Qwen 2.5 VL (FP8 Scaled) | Text Encoder / CLIP | [HuggingFace – Comfy‑Org/Qwen‑Image](https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/tree/main/split_files/text_encoders) |
| Qwen Image VAE | VAE | [HuggingFace – Comfy‑Org/Qwen‑Image](https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/tree/main/split_files/vae) |
| Qwen‑Image‑Lightning (8‑step) | LoRA (speed boost) | [HuggingFace – lightx2v/Qwen‑Image‑2512‑Lightning](https://huggingface.co/lightx2v/Qwen-Image-2512-Lightning) |
| Aldniki Qwen Reality Transform | LoRA (realistic look) | [CivitAI – Search for “aldniki qwen reality transform”](https://civarchive.com/models?query=aldniki+qwen+reality+transform) |
> Note: The last LoRA is hosted on CivitAI. Just search for aldniki qwen reality transform and you’ll find it quickly.
---
## 🔧 How to Use
1. Place the model files in the appropriate ComfyUI folders diffusion_models, text_encoders, vae, loras).
2. Load the provided workflow image (or JSON) into ComfyUI.
3. Adjust the prompts to your liking – the camera and lighting nodes will automatically add professional descriptive text.
4. Hit Queue Prompt and enjoy!
---
## 📥 Download
The workflow JSON is attached to this resource.
Just drag & drop it into your ComfyUI canvas.
---
Have fun creating cinematic masterpieces!
If you run into any issues, feel free to open a GitHub issue or leave a comment here.
---
📬 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!