Why generated images don't always match the character

Worth understanding before you spend a long time troubleshooting, because some of this is a genuine limitation rather than a fault.

The image prompt is written from limited context. We don't use a specialised language model to write image prompts, and the prompt is built from the most recent message and the character's avatar. It doesn't read your whole conversation. So the picture can miss details that seem obvious to you from earlier in the scene.

It works from a single reference image. The result will drift from your character if the avatar is low resolution, shows them at an unusual angle, or has unusual colouring.

The underlying model has known biases. DreamShaper-8 tends towards generating caucasian female figures because of how it was trained, which means skin tone, gender and character consistency aren't always accurate. This is a limitation of the model, not a settings problem.

What helps

Edit the prompt. Select the pencil icon at the bottom right of a generated image to adjust the prompt directly. The AI uses your version as its reference.

Reference the important details in your message, since the last message is what the prompt is built from. If you want a specific outfit or setting in the image, mentioning it in the message you send helps.

Use a clear, front-facing, good-quality avatar as your character's reference image.