# Base Image (img2img)

<figure><img src="https://1638460590-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FsrvmkNlt2cT7tVvQkddJ%2Fuploads%2FsLigg0rEFB9iZJg6SZp4%2Fimage.png?alt=media&#x26;token=1c1139f5-d61e-4ff3-b971-a6fc57d898b9" alt="" width="209"><figcaption></figcaption></figure>

Sometimes using just a prompt isn't enough to get the image you want. Adding in a base image can help guide the AI to getting the desired results.

[variation-strength](https://artroomai.gitbook.io/tutorials/resources/settings-tutorials/variation-strength "mention") plays a large role in the amount of changes when using img2img

<details>

<summary>Settings used in examples</summary>

{% code overflow="wrap" %}

```
"text_prompts": "close up, cute bunny, tall trees, shadows, high noon, god rays",
"negative_prompts": "nude, nsfw, purple, mutated, deformed, amateur drawing, lowres, text, error, signature, watermark, username, blurry, censorship, sketch, monochrome",
"strength": 0.21,
"init_image": "...",
"width": 768,
"height": 768,
"models_dir": "C:\\models\\Artroom",
"ckpt": "Models\\aZovyaPhotorealUltra2GB_v10-fixed.safetensors",
"vae": "mse.vae.pt",
"loras": [],
"controlnet": "none",
"use_preprocessed_controlnet": false,
"remove_background": "face",
"use_removed_background": false,
"sampler": "euler_a",
"steps": 30,
"cfg_scale": 7,
"clip_skip": 1,
"seed": 82413648,
"mask_image": "...",
"invert": false,
"palette_fix": false,
"image_save_path": "C:\\ArtroomOutputs\\img2img",
"n_iter": 1,
"save_grid": false,
"speed": "High",
"long_save_path": false,
"highres_fix": true,
"show_intermediates": true,
"id": "3318777549530247"
```

{% endcode %}

</details>

Without any starting image this is the output image

<figure><img src="https://1638460590-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FsrvmkNlt2cT7tVvQkddJ%2Fuploads%2FiZtrBej3jimqm9s4uDch%2Fimage.png?alt=media&#x26;token=c2aab3c7-d21d-4b78-a8b6-0f0ead08da60" alt="" width="375"><figcaption></figcaption></figure>

\
But placing this starting image in the space provided,&#x20;

<figure><img src="https://1638460590-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FsrvmkNlt2cT7tVvQkddJ%2Fuploads%2FGhqarQsgjhszR3HDckMa%2Fimage.png?alt=media&#x26;token=8b93e5cc-407d-46a7-9db4-118bf5e03f18" alt=""><figcaption></figcaption></figure>

<figure><img src="https://1638460590-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FsrvmkNlt2cT7tVvQkddJ%2Fuploads%2Fac0SM856ZA5IigvFu1Ew%2Fimage.png?alt=media&#x26;token=74aaa5f6-930c-4e56-af2c-72e26d6e81fe" alt=""><figcaption></figcaption></figure>

These are the outputs it generates at different variation strengths.

<figure><img src="https://1638460590-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FsrvmkNlt2cT7tVvQkddJ%2Fuploads%2Fr8BhSBryHEQ0CYRVfEkw%2Fxyplot_strength_0.1_0.2_0.3_0.4_0.5_0.6_0.7_0.8_0.9__.png?alt=media&#x26;token=d084447a-1973-48ae-80ca-a0f7b7f53c15" alt=""><figcaption></figcaption></figure>

Keeping that starting image and other settings but changing the prompt to \
"space ship, red nebula, large star, vibrant" \
will yield this result.

<figure><img src="https://1638460590-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FsrvmkNlt2cT7tVvQkddJ%2Fuploads%2FJO3CA50LLNtHiC5VoCE5%2Fxyplot_strength_0.1_0.2_0.3_0.4_0.5_0.6_0.7_0.8_0.9__.png?alt=media&#x26;token=3cff3033-4cf5-480b-82b3-b87701dfd0c4" alt=""><figcaption></figcaption></figure>

\
[controlnet](https://artroomai.gitbook.io/tutorials/resources/extra-features-tutorials/controlnet "mention") Is anther method for copying details from a base image that follows certain details more accurately.