Generate images directly in Tess's chat using the main visual AI models on the market. You activate 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 pops up right in the chat, integrated into the conversation context.
What is it?
The Images tool in chat lets you:
Create images from text (prompt)
Remake the same image in different models
Apply quick functions like:
Remove background (remover fundo)
Upscale image (melhorar resolução)
SVG vectorize (converter em vetor)
All of 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 quicker adjustments.
How to use?
Step 1 – Open the chat and turn on Images
Step 2 – Pick the image model
In the Images tool, pick one of the available models:
Tess 6
Nano Banana
GPT 5
Ideogram 3
Seedream 4
Kontext Max
Minimax Image
Runway Gen4
Queen
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 chosen text model (LLM) might ask you quick questions about colors, format, or audience to build an optimized prompt for what you need. Share your ideas and let the LLM do the rest. It'll write the prompt and trigger the image AI automatically; you don't need to leave the chat or access another panel.
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 he commented without logos, texts or watermark. So, whenever you want images with details or specific texts, share it in the chat so the text model can help you!
Step 4 – See the result in the chat
The image generated appears right in the conversation.
You can comment on it, ask for variations, change colors, tweak style etc.
When you hover your mouse over the photo, the icons show up. From left to right, they stand for, respectively:
Download: download the generated image to your device
Info: See the prompt, model, and image generation cost
Upscale: Improve the image quality by 2x
Remove background: Use AI to remove the image background, creating a PNG version
Vectorization: Generate a vector of this image in SVG
Open image: To see better, open it and check out your image’s details
Step 5 – Redo by changing the model
One of the cool features is being able to:
Generate the image with a model (e.g.: Nano Banana).
Then, pick another model (e.g.: Ideogram 3 or Runway Gen4).
Ask: “redo with the same style, but with a character standing up drinking tea”.
The LLM reviews the prompt and 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 from an image. Useful for cropping products, creating stickers, building compositions in social media templates
Upscale Image (Melhorar resolução): Increases the resolution and sharpness of the image. Useful for getting pieces ready to print, making images sharper in presentations, avoiding pixelation in video edits.
SVG Vectorize (Converter para vetor): Converts logos, icons, or simple drawings to vector format (SVG). Useful for responsive logos, interface icons, tweaks in vector design tools.
Quick examples of using it in the chat
Instagram post
Let’s get started with Nano Banana:
"I want an image for an Instagram post about anxiety, minimalist style, light background, with an illustration of a person taking a deep breath, in blue and lilac colors."
Then, with Ideogram 3:
"Now use the same image, don't change it, just add the phrase: Breathe, you are not alone'"
Image with readable text
Now let's use GPT 5 Image:
"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."
And then, a simple: "Redo", but with the Tess 6 model
Advantages of creating images right in the chat
Continuous context: the LLM remembers the conversation (brand, persona, campaign) and uses that to improve the prompts.
Fast iteration: you adjust text, color, style, model – all in the same thread.
Real multimodality: text, image, video, music, and audio all in one flow.
Model testing: generate with one model, switch to another and compare styles.
Integrated post-processing: remove background, upscale and vectorize without leaving the chat.
Best practices to improve your image generation in the chat with AI:
Always indicate:
purpose of the image (feed, story, thumb, slide)
style (realistic, illustrated, flat, 3D, minimalist)
main colors
if you need text on the image (and what text)
When you test different models:
keep the same base prompt
ask explicitly: “use the same prompt, but generate with model X”
