# cubiq/comfyui_ipadapter_plus **Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/cubiq-comfyui-ipadapter-plus).** 6,031 stars · 466 forks · Python · GPL-3.0 ## Links - GitHub: https://github.com/cubiq/ComfyUI_IPAdapter_plus - awesome-repositories: https://awesome-repositories.com/repository/cubiq-comfyui-ipadapter-plus.md ## Description ComfyUI_IPAdapter_plus is a node-based extension for ComfyUI that implements IPAdapter models to guide image generation using reference images. It functions as an image prompting tool and a Stable Diffusion image adapter, allowing reference files to serve as visual prompts for controlling style, composition, and subject identity. The project provides specialized capabilities for maintaining facial identity and high-fidelity features across generated portraits. It enables the transfer of visual characteristics and artistic styles from reference images, as well as the extraction of spatial layouts to guide the arrangement of objects in new generations. The extension covers broad functional areas including AI image conditioning, consistent character generation, and image composition control. ## Tags ### Development Tools & Productivity - [ComfyUI Custom Node Suites](https://awesome-repositories.com/f/development-tools-productivity/comfyui-custom-node-suites.md) — Provides a custom node suite for integrating IPAdapter models into ComfyUI workflows. ### Artificial Intelligence & ML - [Image-Prompted Generation](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/diffusion-visual-models/generative-ai-pipelines/text-to-image-generators/image-prompted-generation.md) — Implements a system that treats reference images as visual prompts to control style and composition. - [Cross-Attention Conditioning](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/diffusion-visual-models/generative-ai-pipelines/text-to-video-generators/cross-attention-conditioning.md) — Injects reference image embeddings into the UNet via cross-attention layers to guide the generation process. - [Image-Conditioned Generation](https://awesome-repositories.com/f/artificial-intelligence-ml/image-generation/image-conditioned-generation.md) — Enables the generation of new images using reference files as structural or stylistic baselines. ([source](https://github.com/cubiq/comfyui_ipadapter_plus#readme)) - [Style Transfers](https://awesome-repositories.com/f/artificial-intelligence-ml/image-generation/style-transfers.md) — Applies the artistic style and visual characteristics of a reference image to control the generated output. ([source](https://github.com/cubiq/comfyui_ipadapter_plus#readme)) - [Image Encoder Embedding Extractions](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/domain-specific-processing-pipelines/image-encoder-embedding-extractions.md) — Uses pretrained CLIP vision models to extract numerical embedding representations from reference images. - [Attention Masking](https://awesome-repositories.com/f/artificial-intelligence-ml/attention-masking.md) — Implements attention masking to precisely control which regions of a generation are influenced by reference images. - [Compositional Layout Transfers](https://awesome-repositories.com/f/artificial-intelligence-ml/compositional-layout-transfers.md) — Extracts spatial layouts from reference images to guide the arrangement of objects in new generations. ([source](https://github.com/cubiq/comfyui_ipadapter_plus#readme)) - [Latent Layout Mappings](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/diffusion-visual-models/generative-ai-models/latent-space-generative-models/latent-space-projections/image-to-latent-projections/generative-latent-mappings/latent-layout-mappings.md) — Extracts spatial layout information from reference images to align the structure of the generated output. - [Image Composition Controls](https://awesome-repositories.com/f/artificial-intelligence-ml/image-composition-controls.md) — Provides frameworks for managing the spatial layout and arrangement of subjects using reference images. - [Adapter Projection Layers](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/algorithms/linear-regression-implementations/linear-mixing-layers/adapter-projection-layers.md) — Provides linear projection layers to align image encoder outputs with the dimensionality of model attention layers. - [Weight Scaling Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/model-weight-reconstruction/weight-scaling-integrations.md) — Merges IPAdapter weights into the base diffusion model by scaling layer parameters during the loading process. ### Part of an Awesome List - [Stable Diffusion Ecosystem](https://awesome-repositories.com/f/awesome-lists/ai/stable-diffusion-ecosystem.md) — Extends the Stable Diffusion ecosystem by providing image-based conditioning adapters. ### User Interface & Experience - [Generative Character Consistency](https://awesome-repositories.com/f/user-interface-experience/character-encoding-support/chinese-character-support/customizable-character-models/generative-character-consistency.md) — Ensures visual continuity of a person's identity across multiple high-fidelity generated portraits. - [Identity Consistency](https://awesome-repositories.com/f/user-interface-experience/character-encoding-support/chinese-character-support/customizable-character-models/generative-character-consistency/stylized-portrait-generation/identity-consistency.md) — Maintains high-fidelity facial features and subject identity across different generated portraits. ([source](https://github.com/cubiq/comfyui_ipadapter_plus#readme)) - [Portrait Identity Preservers](https://awesome-repositories.com/f/user-interface-experience/character-encoding-support/chinese-character-support/customizable-character-models/generative-character-consistency/stylized-portrait-generation/identity-consistency/portrait-identity-preservers.md) — Provides a specialized implementation for maintaining facial identity and high-fidelity features in portraits.