Image generation AI and language models respond to prompts in fundamentally different ways. A language model rewards specificity about structure and reasoning. An image model rewards specificity about visual information — subject, style, lighting, composition, and parameters — presented in a particular order. Inject the wrong structure and you get a mediocre output no matter how well you described the image you wanted. Prompt Master’s four image and media templates are calibrated to the syntax, parameter conventions, and known failure modes of each generation platform. Detection is automatic: the template selection happens before you see the output, based on the target tool, the presence of an existing prompt or reference image, and whether the task is generating something new or editing something that exists.Documentation Index
Fetch the complete documentation index at: https://mintlify.com/nidhinjs/prompt-master/llms.txt
Use this file to discover all available pages before exploring further.
Visual Descriptor
Visual Descriptor is the primary template for all text-to-image generation. It structures the prompt in the order that diffusion models weight most heavily: subject first, then style and mood, then technical parameters, then the negative prompt. Reordering these layers produces measurably worse results across all major generation platforms. Detection logic: Target tool is Midjourney, DALL-E 3, Stable Diffusion, Sora, Adobe Firefly, or any generative image/video AI, and the task is creating a new image or video from a text description (no reference image provided).Visual Descriptor structure
Visual Descriptor structure
| Layer | What it carries |
|---|---|
| Subject | The primary element — who or what the image is of, with specific descriptors |
| Style / Medium | The visual style, artistic medium, or photographic genre |
| Mood / Atmosphere | The emotional register — cinematic, melancholic, energetic, serene |
| Lighting | Light source, direction, quality — golden hour, neon, hard shadow, diffused |
| Composition | Framing, perspective, depth of field — wide shot, close-up, Dutch angle |
| Technical detail | Rendering quality descriptors — photorealistic, ultra detailed, 8K, RAW |
| Parameters | Tool-specific flags at the end — --ar, --v, --style, --cfg, steps, etc. |
| Negative prompt | What to exclude — only for tools that accept a separate negative prompt field |
Reference Image Editing
Reference Image Editing is used when the task is modifying an existing image rather than generating a new one from scratch. Prompt Master detects the intent automatically — if your request includes an existing image or explicitly describes editing something that already exists, this template is selected over Visual Descriptor. Detection logic: The user provides a reference image URL or file, or the request uses editing language (“change the background,” “remove the object,” “replace the lighting,” “make the subject wearing a different outfit”). Prompt Master identifies edit intent vs. generate intent and routes accordingly — you do not need to specify which template to use.Reference Image Editing structure
Reference Image Editing structure
| Component | What it carries |
|---|---|
| Reference description | A factual description of what’s in the reference image — grounding the model’s understanding |
| Edit instruction | The specific change to make, described with precision |
| Preserve list | Elements of the original image that must not change |
| Style match | Whether to match the original’s style or introduce a new one |
| Parameters | Tool-specific editing flags — --iw (image weight) for Midjourney, inpainting mask notes for SD |
Edit vs. generate detection is automatic. If you paste a prompt like “change the background of this image to a forest,” Prompt Master routes to Reference Image Editing. If you say “generate an image of a person in a forest,” it routes to Visual Descriptor. You never need to specify the template.
ComfyUI
ComfyUI prompts have a different structure from standard diffusion prompts because ComfyUI is node-based — the positive and negative prompt are separate inputs to specific nodes, and different parts of the workflow (base checkpoint, refiner, ControlNet, LoRA) can accept different prompts. A flat prompt string pasted into ComfyUI will work, but a prompt written specifically for the node architecture produces significantly better results. Detection logic: Target tool is explicitly ComfyUI, or the user mentions a node-based workflow, SDXL with a refiner, ControlNet conditioning, or a LoRA stack.ComfyUI template structure
ComfyUI template structure
| Component | What it carries |
|---|---|
| Positive prompt (base checkpoint) | Main subject and composition — written for the base model’s training data |
| Positive prompt (refiner) | Detail and quality descriptors — written for the refiner’s upscaling pass |
| Negative prompt | Explicit exclusions — comma-separated, targeted at the base checkpoint’s known failure modes |
| ControlNet note | If ControlNet conditioning is in use: what type of conditioning and what it should enforce |
| LoRA weights | If LoRAs are active: name, trigger word, and recommended weight |
| Sampler settings | Recommended steps, CFG scale, and sampler for the described output |
Prompt Decompiler
The Prompt Decompiler is a meta-template — it doesn’t generate a new prompt, it operates on an existing one. When you paste a prompt into Prompt Master and ask to break it down, adapt it, simplify it, or split it into components, the Prompt Decompiler activates. It identifies the framework the original prompt was using, labels its components, diagnoses problems, and produces the requested transformation. Detection logic: The user pastes an existing prompt and uses any of the following intent signals: “break this down,” “explain this prompt,” “simplify this,” “adapt this for [different tool],” “split this into two prompts,” “what framework is this using,” or pastes a prompt with no other context (Prompt Master defaults to decompilation mode for bare prompt pastes).Prompt Decompiler outputs
Prompt Decompiler outputs
| Output type | What it produces |
|---|---|
| Decomposition | Labels each part of the original prompt with its function and the framework it belongs to |
| Diagnosis | Identifies anti-patterns, token waste, missing components, and conflicts |
| Simplification | Strips non-load-bearing language while preserving the prompt’s effective instructions |
| Adaptation | Rewrites the prompt for a different target tool using the correct template for that tool |
| Split | Divides a bloated single prompt into two or more focused prompts |
Image Template Detection Summary
How Prompt Master decides which image template to use
How Prompt Master decides which image template to use
| Signal | Template selected |
|---|---|
| Target: Midjourney, DALL-E, SD, Sora, Firefly + no reference image | Visual Descriptor |
| Reference image provided, or editing language detected | Reference Image Editing |
| Target: ComfyUI, or node-based workflow / LoRA / ControlNet mentioned | ComfyUI |
| Existing prompt pasted + break down / adapt / simplify / split intent | Prompt Decompiler |
| Existing prompt pasted with no other context | Prompt Decompiler (default) |