# Complete Feature & Chain Definitions Configuration for MCP Tools # Every chain injector in chain_injectors/ corresponds 1-to-1 with an entry here (21 injectors total). lora: chains: lora display_name: "LoRA Fine-tuning Injector" description: "Injects LoRA weights into UNet/DiT model and CLIP text encoder for custom style, character, or domain adaptation. Note: For Civitai, specify the Version ID (modelVersionId) instead of the main Model ID." max_count: 5 usage_guideline: "Specify source ('Civitai', 'Hugging Face', or 'Upload File'). For Civitai, provide lora_value as the Version ID (modelVersionId). For Hugging Face, provide HF repo file path. For Upload File, provide uploaded filename. Scale (0.0~2.0) controls weight strength." parameters_schema: type: object properties: source: type: string enum: ["Civitai", "Hugging Face", "Upload File"] description: "Download/upload source for the LoRA model. Use 'Civitai' to download by Version ID (modelVersionId), 'Hugging Face' to download by repo file path, or 'Upload File' for uploaded files." lora_value: type: string description: "For Civitai: the Version ID (modelVersionId). For Hugging Face: repo_id/filename.extension or repo_id/folder_path/filename.extension. For Upload File: uploaded filename." scale: type: number default: 1.0 minimum: 0.0 maximum: 2.0 description: "Unified strength applied to both the UNet/DiT model and CLIP text encoder (0.0 to 2.0)." required: - source - lora_value ipadapter: chains: ipadapter display_name: "IP-Adapter Image Prompt" description: "Uses reference images to guide generation style, composition, structure, or face appearance without prompt text restrictions (SD1.5 & SDXL)." max_count: 5 usage_guideline: "Supply global settings (preset, embeds_scaling, combine_method, final_weight) and up to 5 reference images with individual weights. Preset must match the target model architecture (SD1.5 or SDXL)." parameters_schema: type: object properties: image: type: string description: "Reference image encoded as Base64 Data URI (e.g., data:image/png;base64,...) or HTTP/HTTPS URL." weight: type: number default: 1.0 minimum: 0.0 maximum: 2.0 description: "Influence weight of the individual image prompt (0.0 to 2.0)." preset: type: string default: "STANDARD (medium strength)" description: "IPAdapter preset model variant loaded from ipadapter.yaml. Must match model architecture (SD1.5 vs SDXL)." embeds_scaling: type: string default: "V only" enum: - "V only" - "K+V" - "K+V w/ C penalty" - "K+mean(V) w/ C penalty" description: "Embedding scaling method for IPAdapter." combine_method: type: string default: "concat" enum: - "concat" - "add" - "subtract" - "average" - "norm average" - "max" - "min" description: "Combination method for multiple reference images." final_weight: type: number default: 1.0 minimum: 0.0 maximum: 2.0 description: "Global weight multiplier for IPAdapter conditioning (0.0 to 2.0)." lora_strength: type: number default: 0.6 description: "LoRA weight strength for FaceID adapter variants." required: - image controlnet: chains: controlnet display_name: "ControlNet Spatial Guidance" description: "Applies structural and spatial conditioning (depth, pose, lineart, tile, scribble, canny) to guide output composition." max_count: 5 usage_guideline: "Specify ControlNet type and series (must match requested model architecture e.g., SD1.5, SDXL, SD3.5, FLUX.1, Qwen-Image), pre-processed control image (Base64 Data URI or HTTP/HTTPS URL; system does NOT pre-process raw RGB images), and guidance strength." parameters_schema: type: object properties: type: type: string description: "ControlNet conditioning type (must match model architecture)." series: type: string description: "ControlNet model series (must match model architecture)." image: type: string description: "Pre-processed control image (e.g., Depth, Canny, Pose, Lineart map) encoded as Base64 Data URI or HTTP/HTTPS URL. Note: System does NOT automatically pre-process raw RGB images." strength: type: number default: 1.0 minimum: 0.0 maximum: 2.0 description: "Control influence strength (0.0 to 2.0)." required: - type - series - image conditioning: chains: conditioning display_name: "Regional Conditioning / Area Prompt" description: "Defines rectangular areas (X, Y, Width, Height) and assigns specific text prompts and conditioning strengths to them." max_count: 10 usage_guideline: "Define rectangular spatial areas (X, Y, width, height) and assign specific prompts and strengths to them. Supports up to 10 area prompts." parameters_schema: type: object properties: prompt: type: string description: "Text prompt for this specific rectangular area." x: type: integer default: 0 description: "Top-left X coordinate of the rectangular area." y: type: integer default: 0 description: "Top-left Y coordinate of the rectangular area." width: type: integer default: 512 description: "Width of the rectangular area." height: type: integer default: 512 description: "Height of the rectangular area." strength: type: number default: 1.0 minimum: 0.1 maximum: 2.0 description: "Conditioning strength for this area (0.1 to 2.0)." required: - prompt vae: chains: vae display_name: "Custom VAE Loader" description: "Overrides default VAE model used for latent space encoding and final image decoding." max_count: 1 usage_guideline: "Specify source ('Civitai', 'Hugging Face', or 'Upload File'), then provide the vae_value (Civitai Version ID, HF file path, or uploaded filename)." parameters_schema: type: object properties: source: type: string enum: ["Civitai", "Hugging Face", "Upload File"] description: "Download/upload source for the VAE model. Use 'Civitai' to download by Version ID, 'Hugging Face' to download by repo path, or 'Upload File' for uploaded file." vae_value: type: string description: "For Civitai: the Version ID (e.g., '456' from civitai.com/models/123?modelVersionId=456). For Hugging Face: repo_id/filename.extension or repo_id/folder_path/filename.extension (e.g., 'madebyollin/sdxl-vae-fp16-fix/sdxl_vae.safetensors'). For Upload File: uploaded file name." required: - source - vae_value pid: chains: pid display_name: "PiD High-Resolution Refinement" description: "Progressive Detail (PiD) upscale injector for fine detail enhancement and resolution upscaling." max_count: 1 usage_guideline: "Enables PiD detail refinement pipeline using a boolean switch ('enabled': true/false)." parameters_schema: type: object properties: enabled: type: boolean default: true description: "Enable or disable PiD High-Resolution Refinement." required: - enabled flux1_style: chains: style display_name: "FLUX.1 Style Reference" description: "Applies artistic style conditioning from reference images onto FLUX.1 model generated outputs." max_count: 5 usage_guideline: "Supply style reference image(s) (up to 5) encoded as Base64 Data URI or HTTP/HTTPS URL and optional strength." parameters_schema: type: object properties: image: type: string description: "Style reference image encoded as Base64 Data URI or HTTP/HTTPS URL." strength: type: number default: 1.0 minimum: 0.0 maximum: 2.0 description: "Style influence strength (0.0 to 2.0)." required: - image reference_edit: chains: reference_latent display_name: "Reference Edit" description: "For multimodal models, this feature enables powerful editing and combining capabilities. In txt2img mode, adding a single reference image performs an Image Edit, while adding multiple images performs an Image Combine." max_count: 10 usage_guideline: "Supply reference image(s) encoded as Base64 Data URI or HTTP/HTTPS URL. Passing a single reference image performs an Image Edit, while passing multiple images (up to 10) performs an Image Combine." parameters_schema: type: object properties: image: type: string description: "Reference image encoded as Base64 Data URI or HTTP/HTTPS URL." required: - image mage_flow_reference_edit: chains: reference_image display_name: "Reference Image Edit" description: "For multimodal models, this feature enables reference image editing and combining capabilities. In txt2img mode, adding a single reference image performs an Image Edit, while adding multiple images performs an Image Combine." max_count: 10 usage_guideline: "Supply reference image as Base64 Data URI or HTTP/HTTPS URL." parameters_schema: type: object properties: image: type: string description: "Reference image encoded as Base64 Data URI or HTTP/HTTPS URL." required: - image fibo2_reference_edit: chains: reference_image display_name: "Fibo-2.0 Reference Edit" description: "For Fibo 2.0 models, this feature enables reference image editing and combining capabilities. In txt2img mode, adding a single reference image performs an Image Edit, while adding multiple images performs an Image Combine." max_count: 10 usage_guideline: "Supply reference image as Base64 Data URI or HTTP/HTTPS URL." parameters_schema: type: object properties: image: type: string description: "Reference image encoded as Base64 Data URI or HTTP/HTTPS URL." required: - image minimax_h3_image_reference_edit: chains: reference_image display_name: "MiniMax-H3-Image Reference Edit" description: "For MiniMax-H3-Image, this feature enables reference image editing and combining capabilities. In txt2img mode, adding a single reference image performs an Image Edit, while adding multiple images performs an Image Combine. The prompt refers to them as , , ..." max_count: 8 usage_guideline: "Supply reference image(s) encoded as Base64 Data URI or HTTP/HTTPS URL (up to 8). Refer to them in the prompt as , , ...; is the picture to edit." parameters_schema: type: object properties: image: type: string description: "Reference image encoded as Base64 Data URI or HTTP/HTTPS URL." required: - image p_h3_image_reference_edit: chains: reference_image display_name: "P-H3-Image Reference Edit" description: "For P-H3-Image, this feature enables reference image editing and combining capabilities. In txt2img mode, adding a single reference image performs an Image Edit, while adding multiple images performs an Image Combine. The prompt refers to them as , , ..." max_count: 8 usage_guideline: "Supply reference image(s) encoded as Base64 Data URI or HTTP/HTTPS URL (up to 8). Refer to them in the prompt as , , ...; is the picture to edit. Note: steps and cfg are fixed by the model (8-step ManualSigmas grid, no CFG)." parameters_schema: type: object properties: image: type: string description: "Reference image encoded as Base64 Data URI or HTTP/HTTPS URL." required: - image krea2_identity_edit: chains: krea2_identity_edit display_name: "KREA2 Identity Edit" description: "Processed using the lbouaraba/comfyui-krea2edit node. (Krea-2-Turbo recommended, Krea-2-Raw need set ZeroGPU Duration (s) to 120 ) In txt2img mode, adding a single reference image performs an Image Edit, while adding multiple images performs an Image Combine." max_count: 2 usage_guideline: "Supply reference image as Base64 Data URI or HTTP/HTTPS URL." parameters_schema: type: object properties: image: type: string description: "Reference image encoded as Base64 Data URI or HTTP/HTTPS URL." required: - image krea2_style_reference: chains: krea2_style_reference display_name: "KREA2 Style Reference" description: "(Krea-2-Turbo recommended) Add style reference images to perform style reference editing." max_count: 3 usage_guideline: "Supply style reference image as Base64 Data URI or HTTP/HTTPS URL." parameters_schema: type: object properties: image: type: string description: "Style reference image encoded as Base64 Data URI or HTTP/HTTPS URL." required: - image joyai_reference_edit: chains: joyai_image display_name: "JoyAI Reference Edit" description: " (JoyAI-Image-Edit recommended) For multimodal models, this feature enables powerful editing and combining capabilities. In txt2img mode, adding a single reference image performs an Image Edit (JoyAI-Image-Edit recommended), while adding multiple images performs an Image Combine (JoyAI-Image-Edit-Plus recommended with ZeroGPU Duration (s) set to 120)." max_count: 2 usage_guideline: "Supply JoyAI reference image as Base64 Data URI or HTTP/HTTPS URL." parameters_schema: type: object properties: image: type: string description: "Input reference image encoded as Base64 Data URI or HTTP/HTTPS URL." required: - image qwen_image_edit: chains: qwen_image_edit display_name: "Qwen-Image Edit" description: " (lightx2v/Qwen-Image-Edit-2511-Lightning recommended) In txt2img mode, adding a single reference image performs an Image Edit, while adding multiple images performs an Image Combine." max_count: 3 usage_guideline: "Supply reference image(s) (up to 3) encoded as Base64 Data URI or HTTP/HTTPS URL. Passing a single reference image performs an Image Edit, while passing multiple images performs an Image Combine." parameters_schema: type: object properties: image: type: string description: "Reference image encoded as Base64 Data URI or HTTP/HTTPS URL." required: - image hidream_o1_smoothing: chains: hidream_o1_smoothing display_name: "HiDream O1 Smoothing Injector" description: "HiDream O1 detail smoothing and artifact reduction injector." max_count: 1 usage_guideline: "Configures smoothing factor for HiDream models." parameters_schema: type: object properties: factor: type: number default: 0.5 description: "Smoothing intensity (0.0 to 1.0)." required: [] hidream_o1_reference: chains: hidream_o1_reference display_name: "HiDream-O1 Reference Edit" description: " (HiDream-O1-Image-Dev recommended with resolution set to 4.0MP, e.g., 2048x2048) For HiDream-O1 models, this feature enables reference image editing and combining capabilities. In txt2img mode, adding a single reference image performs an Image Edit, while adding multiple images performs an Image Combine." max_count: 9 usage_guideline: "Supply reference image(s) (up to 9) encoded as Base64 Data URI or HTTP/HTTPS URL. Passing a single reference image performs an Image Edit, while passing multiple images performs an Image Combine." parameters_schema: type: object properties: image: type: string description: "Reference image encoded as Base64 Data URI or HTTP/HTTPS URL." required: - image sensenova_reference: chains: sensenova_reference display_name: "SenseNova Reference Edit" description: "For SenseNova models, this feature enables reference image editing and combining capabilities. In txt2img mode, adding a single reference image performs an Image Edit, while adding multiple images performs an Image Combine." max_count: 10 usage_guideline: "Supply reference image(s) (up to 10) encoded as Base64 Data URI or HTTP/HTTPS URL. Passing a single reference image performs an Image Edit, while passing multiple images performs an Image Combine." parameters_schema: type: object properties: image: type: string description: "Reference image encoded as Base64 Data URI or HTTP/HTTPS URL." required: - image flux1_ipadapter: chains: flux1_ipadapter display_name: "Flux1 IP-Adapter" description: "FLUX.1 model-specific IP-Adapter implementation." max_count: 5 usage_guideline: "Supply reference image (Base64 Data URI or HTTP/HTTPS URL), optional weight (default 1.0), start_at (default 0.0), and end_at (default 1.0). Up to 5 images supported." parameters_schema: type: object properties: image: type: string description: "Reference image encoded as Base64 Data URI or HTTP/HTTPS URL." weight: type: number default: 1.0 description: "Influence weight of the image prompt (0.0 to 2.0)." start_at: type: number default: 0.0 description: "Start step percentage for IP-Adapter application (0.0 to 1.0)." end_at: type: number default: 1.0 description: "End step percentage for IP-Adapter application (0.0 to 1.0)." start_percent: type: number default: 0.0 description: "Alias for start_at." end_percent: type: number default: 1.0 description: "Alias for end_at." required: - image sd3_ipadapter: chains: sd3_ipadapter display_name: "SD3 IP-Adapter" description: "SD3/SD3.5 model-specific IP-Adapter implementation." max_count: 5 usage_guideline: "Supply reference image (Base64 Data URI or HTTP/HTTPS URL), optional weight (default 1.0), start_at (default 0.0), and end_at (default 1.0). Up to 5 images supported." parameters_schema: type: object properties: image: type: string description: "Reference image encoded as Base64 Data URI or HTTP/HTTPS URL." weight: type: number default: 1.0 description: "Influence weight of the image prompt (0.0 to 2.0)." start_at: type: number default: 0.0 description: "Start step percentage for IP-Adapter application (0.0 to 1.0)." end_at: type: number default: 1.0 description: "End step percentage for IP-Adapter application (0.0 to 1.0)." start_percent: type: number default: 0.0 description: "Alias for start_at." end_percent: type: number default: 1.0 description: "Alias for end_at." required: - image embedding: chains: embedding display_name: "Textual Inversion Embedding Injector" description: "Downloads Textual Inversion embedding files from Civitai, Hugging Face, or uploads to the server. Note: This feature ONLY handles file downloading/preparation. To activate the embedding, manually add 'embedding:' (e.g. 'embedding:civitai/456' for Civitai ID 456, 'embedding:huggingface/lazypos' for Hugging Face, or 'embedding:upload_file/filename' for uploaded files) into your prompt or negative_prompt." max_count: 5 usage_guideline: "Specify source ('Civitai', 'Hugging Face', or 'Upload File'), and embedding_value (Civitai Version ID, HF repo file path, or uploaded filename). The file is stored on server; manually enter 'embedding:' in prompt or negative_prompt to activate." parameters_schema: type: object properties: source: type: string enum: - "Civitai" - "Hugging Face" - "Upload File" description: "Download source for the Textual Inversion embedding file. Use 'Civitai' to download by Version ID, 'Hugging Face' to download by repo file path, or 'Upload File' for uploaded files." embedding_value: type: string description: "For Civitai: the Version ID (e.g., '456' from civitai.com/models/123?modelVersionId=456, saved as 'civitai/456.safetensors'). For Hugging Face: repo_id/filename.extension (e.g., 'ilikebigturtles/lazypos/lazypos.safetensors', saved as 'huggingface/lazypos.safetensors'). For Upload File: uploaded filename (saved as 'upload_file/filename.safetensors'). Manually reference embedding: in prompt or negative_prompt." required: - source - embedding_value prompt_enhancer: chains: prompt_enhancer display_name: "Prompt Enhancer Settings" description: "Enhance or upsample prompts with any registered prompt-enhancer model (Qwen-Image-2.1 PE T2I/I2I, Qwen3.8-27B, Qwen3.5-9B, Qwen3-VL-4B-Instruct, FLUX.3 Prompt Upsampler, P-H3-Image Prompt Upsampler), optional reasoning CoT thinking mode, and optional system prompt. The clip and system_prompt registries are independent, so they are freely mixable across architectures." max_count: 1 usage_guideline: "Set enable to true to activate prompt enhancement. Pick model from the clip registry and system_prompt from the system_prompt registry in yaml/prompt_enhancer.yaml; both lists are global, so any architecture may select any clip paired with any system prompt. Defaults for each framework come from the architecture section and reset when the base model changes. architecture[framework].clip_type is the framework's own encoder and applies to whatever clip is selected, so a prompt upsampler built for one vendor still runs under another framework's encoder. Nothing is auto-detected from images, so an explicit system prompt always wins. Enable thinking for reasoning CoT (reasoning tags are stripped from the result), and set max_length for generation length." parameters_schema: type: object properties: enable: type: boolean default: false description: "Enable prompt enhancement." thinking: type: boolean default: false description: "Enable thinking (reasoning CoT). Thought text inside tags is automatically stripped before the prompt reaches downstream text encoding." model: type: string description: "Prompt Enhancer Model name from the clip registry in yaml/prompt_enhancer.yaml (e.g. Qwen-Image-2.1-Prompt-Enhancer-T2I, Qwen3.8-27B, Qwen3.5-9B, Qwen3-VL-4B-Instruct, Qwen3.5-9B-FLUX.3-Prompt-Upsampler, PrunaAI/P-H3-Image-Prompt-Upsampler). Any model may select any registered clip regardless of architecture. The CLIPLoader type is the framework's, not the checkpoint's: architecture[framework].clip_type applies to whatever clip is selected (same Qwen3.5-9B weights load as `minimax` for MiniMax-H3-Image and `moss_image` for MOSS-Image), so a Qwen-Image-2.1 upsampler still runs as `moss_image` under MOSS-Image. A clip entry may also declare its own clip_type for calls without framework context. Defaults to the architecture entry for the active framework." system_prompt: type: string description: "System Prompt name from the system_prompt registry in yaml/prompt_enhancer.yaml (e.g. none, Ming-Image-PE-Template, FLUX.3-T2I-PE-Template, FLUX.3-I2I-PE-Template, FLUX.3-T2I-Bbox-PE-Template, FLUX.3-I2I-Bbox-PE-Template). Independent of the selected clip and never inferred from images; an empty prompt means no system prompt." max_length: type: integer default: 4096 description: "Maximum generation length for prompt enhancement (default 4096)." moss_image_control: chains: moss_image_control display_name: "MOSS-Image Color/Depth Control" description: "Controls MOSS-Image generation using a color region map (object/region spatial layout) and/or a depth map (3D spatial depth, near is white) via Comfy-Org/MOSS-Image color/depth control LoRA and MOSSImageControl node." max_count: 1 usage_guideline: "Supply color_map (RGB region ID map) and/or depth_map (near=white grayscale map) as Base64 Data URI or HTTP/HTTPS URL. Set strength (default 1.0) and timestep range (start_percent 0.0, end_percent 0.5)." parameters_schema: type: object properties: color_map: type: string description: "Color region map image encoded as Base64 Data URI or HTTP/HTTPS URL. Each region uses a flat RGB color as a region ID." depth_map: type: string description: "Depth map image encoded as Base64 Data URI or HTTP/HTTPS URL (near is white, far is dark)." strength: type: number default: 1.0 minimum: 0.0 maximum: 2.0 description: "Control influence strength multiplier (default 1.0)." start_percent: type: number default: 0.0 minimum: 0.0 maximum: 1.0 description: "Sampling percentage at which control begins (default 0.0)." end_percent: type: number default: 0.5 minimum: 0.0 maximum: 1.0 description: "Sampling percentage at which control ends (default 0.5, use 0.5 for 3D mannequin)." moss_image_edit: chains: moss_image_edit display_name: "MOSS-Image Edit" description: "Edits images or generates variants using MOSS-Image Edit LoRA (officially packaged by Comfy-Org as moss_image_edit_lora_rank_64_bf16.safetensors) and native TextEncodeMOSSImageEdit node." max_count: 10 usage_guideline: "Upload 1-10 reference images and specify prompt. Automatically uses the official MOSS-Image Edit LoRA layout." parameters_schema: type: object properties: images: type: array items: type: string description: "List of 1 to 10 reference images encoded as Base64 Data URI, HTTP/HTTPS URL, or local file path."