npx claudepluginhub replicate/skills --plugin prompt-imagesThis skill uses the workspace's default tool permissions.
Distilled from Replicate's blog posts on prompting image models (2024-2026). Techniques are model-agnostic and focus on transferable principles. For model selection, pricing, and feature comparison, see the [compare-models](../compare-models/SKILL.md) skill.
Generates images from text, edits images with references, performs product placement, style transfer, and multi-image composition using OpenAI DALL-E or Google Gemini.
Enhances AI image generation prompts with Subject-Context-Style structure, style anchors, character consistency, and mcp-image workflows. Improves prompt quality for better results.
Generates optimized prompts for Gemini 2.5 Flash Image (Nano Banana) using best practices for photorealistic shots, art styles, and multi-turn editing workflows.
Share bugs, ideas, or general feedback.
Distilled from Replicate's blog posts on prompting image models (2024-2026). Techniques are model-agnostic and focus on transferable principles. For model selection, pricing, and feature comparison, see the compare-models skill.
Write full sentences describing what you want. Modern image models understand grammar and context far better than keyword-stuffed prompts.
Good: "A woman standing in a Tokyo alleyway at dusk, neon signs reflecting off wet pavement" Bad: "woman, Tokyo, alleyway, dusk, neon, wet pavement"
Name exact colors, materials, lighting setups, camera equipment, and spatial relationships. Vague terms like "make it better" or "artistic" give unpredictable results.
Good: "A brutalist concrete building reflected in a perfectly still puddle after rain. A single figure with a red umbrella walks along the edge, the only color in an otherwise monochrome scene. Overcast sky, flat diffused light, tilt-shift lens effect on the edges." Bad: "Cool building with a person near it, rainy day"
Use descriptive phrases like "the woman with short black hair" or "the red car." Avoid pronouns, which are often too ambiguous for image models.
Most modern models accept thousands of tokens. Long descriptive prompts with clear structure outperform short ones. A prompt with 12+ specific requirements (text on objects, labeled diagrams, color-coded elements, specific materials) can work if each requirement is stated clearly. But be aware: the longer and more complex the prompt, the more likely something will be missed.
Begin with basic changes. Test small edits first, then build on what works. Most editing models support iterative editing, so take advantage of that.
Modern image models understand camera and photography terminology deeply. Using this vocabulary gives you precise control over the look.
Rendering text in images is a common task. These techniques improve accuracy across models.
Maintaining the same character across multiple generations is one of the hardest challenges in image generation.
Some models can generate multiple related images in a single prompt.
Keyword-stuffed prompts: Modern models respond better to natural language sentences than comma-separated keyword lists. Write like you're describing a scene, not tagging a photo.
Using "transform" when you want a small edit: "Transform the person into a Viking" may swap the entire identity. Use targeted language: "change her outfit to Viking armor, keeping her face and expression unchanged."
Not specifying what to keep: When editing, always say what should stay the same. Without explicit instructions, models may change anything.
Negative prompts on models not trained for them: Some models were not trained with negative prompts. Using them on these models introduces noise rather than removing unwanted elements. Check the model's documentation.
Too-high guidance scale (CFG): If images look "burnt" with excessive contrast, lower the guidance scale. Each model has a recommended range.
Expecting real-time knowledge: No image model has internet access. Some have strong world knowledge baked in from training data, but it's not live.
Short prompts for complex scenes: Modern models accept thousands of tokens. For complex compositions with many specific requirements, use that capacity.
Ignoring aspect ratio: Most models have specific resolutions they work best at (commonly ~1 megapixel). Going too large produces edge artifacts. Going too small produces harsh crops. Use the model's recommended aspect ratios.
Wrong model for the task: Not every model is good at every task. Some excel at text rendering but struggle with object removal. Some are great at style transfer but poor at background editing. If a model struggles with a specific edit type, try a different one rather than fighting the prompt. See the compare-models skill for guidance.
Not iterating: The best results come from iterative workflows. Make a small change, evaluate, refine, repeat. Don't try to get everything right in a single generation.
All techniques in this skill are sourced from Replicate's blog: