DOCS.md

Usage

TL;DR: Enter a prompt or roll the 🎲 and press Generate.

Prompting

Positive and negative prompts are embedded by Compel for weighting. See syntax features to learn more.

Use + or - to increase the weight of a token. The weight grows exponentially when chained. For example, blue+ means 1.1x more attention is given to blue, while blue++ means 1.1^2 more, and so on. The same applies to -.

Groups of tokens can be weighted together by wrapping in parantheses and multiplying by a float between 0 and 2. For example, (masterpiece, best quality)1.2 will increase the weight of both masterpiece and best quality by 1.2x.

This is the same syntax used in InvokeAI and it differs from AUTOMATIC1111:

Compel	AUTOMATIC1111
blue++	((blue))
blue--	[[blue]]
(blue)1.2	(blue:1.2)
(blue)0.8	(blue:0.8)

Models

Each model checkpoint has a different aesthetic:

• Comfy-Org/stable-diffusion-v1-5: base
• cyberdelia/CyberRealistic_V5: realistic
• Lykon/dreamshaper-8: general purpose (default)
• fluently/Fluently-v4: general purpose stylized
• Linaqruf/anything-v3-1: anime
• prompthero/openjourney-v4: Midjourney art style
• SG161222/Realistic_Vision_V5: realistic
• XpucT/Deliberate_v6: general purpose stylized

LoRA

Apply up to 2 LoRA (low-rank adaptation) adapters with adjustable strength:

• Perfection Style: attempts to improve aesthetics, use high strength
• Detailed Style: attempts to improve details, use low strength

NB: The trigger words are automatically appended to the positive prompt for you.

Embeddings

Select one or more textual inversion embeddings:

• fast_negative: all-purpose (default, recommended)
• cyberrealistic_negative: realistic add-on (for CyberRealistic)
• unrealistic_dream: realistic add-on (for RealisticVision)

NB: The trigger token is automatically appended to the negative prompt for you.

Styles

Styles are prompt templates that wrap your positive and negative prompts. They were originally derived from the twri/sdxl_prompt_styler Comfy node, but have since been entirely rewritten.

Start by framing a simple subject like portrait of a cat or landscape of a mountain range and experiment.

Anime

The Anime: * styles work the best with Dreamshaper. When using the anime-specific Anything model, you should use the Anime: Anything style with the following settings:

• Scheduler: DEIS 2M or DPM++ 2M
• Guidance: 10
• Steps: 50

You subject should be a few simple tokens like girl, brunette, blue eyes, armor, nebula, celestial. Experiment with Clip Skip and Karras. Finish with the Perfection Style LoRA on a moderate setting and upscale.

Scale

Rescale up to 4x using Real-ESRGAN with weights from ai-forever. Necessary for high-resolution images.

Image-to-Image

The Image-to-Image settings allows you to provide input images for the initial latents, ControlNet, and IP-Adapter.

Strength

Initial image strength (known as denoising strength) is essentially how much the generation will differ from the input image. A value of 0 will be identical to the original, while 1 will be a completely new image. You may want to also increase the number of inference steps.

💡 Denoising strength only applies to the Initial Image input; it doesn't affect ControlNet or IP-Adapter.

ControlNet

In ControlNet, the input image is used to get a feature map from an annotator. These are computer vision models used for tasks like edge detection and pose estimation. ControlNet models are trained to understand these feature maps. Read the Diffusers docs to learn more.

Currently, the only annotator available is Canny (edge detection).

IP-Adapter

In an image-to-image pipeline, the input image is used as the initial latent. With IP-Adapter, the input image is processed by a separate image encoder and the encoded features are used as conditioning along with the text prompt.

For capturing faces, enable IP-Adapter Face to use the full-face model. You should use an input image that is mostly a face and it should be high quality. You can generate fake portraits with Realistic Vision to experiment.

Advanced

DeepCache

DeepCache caches lower UNet layers and reuses them every Interval steps. Trade quality for speed:

• 1: no caching (default)
• 2: more quality
• 3: balanced
• 4: more speed

FreeU

FreeU re-weights the contributions sourced from the UNet’s skip connections and backbone feature maps. Can sometimes improve image quality.

Clip Skip

When enabled, the last CLIP layer is skipped. Can sometimes improve image quality.

Tiny VAE

Enable madebyollin/taesd for near-instant latent decoding with a minor loss in detail. Useful for development.