Generate images directly in Tess’s chat using the main visual AI models on the market. You turn on the Images tool, pick the model, and describe what you want to see. The LLM helps you write the prompt and triggers the image AI – the result shows up right in the chat, integrated with the conversation context.
What is it?
The Images tool in the chat lets you:
Create images from text (prompt)
Recreate the same image in different models
Apply quick functions like:
Remove background (remover fundo)
Upscale image (melhorar resolução)
SVG vectorize (converter em vetor)
All this without leaving the conversation: the previous context (brand, visual reference, persona, post objective, etc.) is used by the LLM to suggest better prompts and faster tweaks.
How to use it?
Step 1 – Open the chat and enable Images
Step 2 – Choose the image model
In the Images tool, select one of the available models.
You can try the same prompt in different models to compare styles and quality.
Step 3 – Ask for the image (the LLM helps with the prompt)
Write in natural language what you want:
“I want a minimalist Instagram post about mental health, light background, female character, flat style”
Depending on your request, the selected text model (LLM) may ask you quick questions about colors, format, audience to build an optimized prompt for your needs. Share your ideas and let the LLM do the rest. It will write the prompt and trigger the image AI automatically; you don’t need to leave the chat or access another panel. That’s the power of multi-model collaboration!
In the example above, ChatGPT 5.2 helped us structure the prompt:
Minimalist Instagram post about mental health, clean light off-white background with lots of negative space, flat vector illustration style. Center-left a calm female character (adult woman) sitting cross-legged in a simple pose, eyes closed, gentle smile, hands on knees, subtle breathing lines near chest. Simple shapes, smooth pastel palette (sage green, muted blue, soft terracotta), thin outlines, no gradients, no textures, no shadows. Add a small abstract plant and a soft rounded shape behind her for balance. No text, no logos, no watermark. Modern, soothing, Scandinavian minimal design. High resolution, crisp edges.
Notice that the prompt asks for the photo without logos, text, or watermark. So whenever you want images with specific details or text, share it in the chat so the text model can help you!
Step 4 – View the result in the chat
The generated image appears directly in the conversation.
You can comment on it, ask for variations, change colors, tweak the style, etc.
When you hover your mouse over the photo, the icons appear; from left to right, they represent, respectively:
Download: download the generated image to your device
Information: See the prompt, model, and cost for generating the image
Upscale: Improve the image quality by 2x
Remove background: Use AI to remove the image background, generating a PNG version
Vectorization: Generate a vector of this image in SVG
Open image: To see it better, open it and check your image’s details
Step 5 – Redo by changing the model
One of the differentiators is being able to:
Generate the image with one model (e.g.: Nano Banana).
Then pick another model (e.g.: Ideogram 3 or Runway Gen4).
Ask: “redo it with the same aesthetic, but with the character standing and drinking tea”.
The LLM reviews the prompt and the context and automatically calls the new model to generate the image.
Extra functions (image post-processing)
Besides generating images from scratch, you can use specific functions directly in the chat:
Remove background (Remover fundo): Automatically removes the background of an image. Useful for cutting out products, creating stickers, building compositions in social media templates.
Upscale Image (Melhorar resolução): Increases the resolution and improves the sharpness of the image. Useful for preparing pieces for print, making images sharper in presentations, avoiding pixelation in video crops.
SVG Vectorize (Converter para vetor): Converts logos, icons or simple drawings into vector format (SVG). Useful for responsive logos, interface icons, adjustments in vector design tools.
Quick examples of how to use it in chat
Instagram post
“I want an image for an Instagram post about anxiety, minimalist style, light background, with an illustration of a person taking a deep breath, colors in blue and lilac.”
Image with readable text
“Create an e-book cover in Portuguese with the title ‘Guia Prático de IA para Negócios’, modern style, purple and white colors, no photos of people.”
Advantages of creating images directly in the chat
Continuous context: the LLM remembers the conversation (brand, persona, campaign) and uses that to improve the prompts.
Fast iteration: you tweak text, color, style, model – all in the same thread.
Real multimodality: text, image, video, music, and audio in the same flow.
Model testing: generate with one model, switch to another and compare styles.
Integrated post-processing: remove background, do upscale and vectorization without leaving the chat.
Best practices to improve your image generation in chat with AI:
Always specify:
goal of the image (feed, story, thumb, slide)
style (realistic, illustrated, flat, 3D, minimalist)
main colors
if you need text in the image (and what text)
When you’re testing different models:
keep the same base prompt
ask explicitly: “use the same prompt, but generate with model X”
