Skip to content
WorkflowListedExternal
Open source

Detection / Image to Prompt — v2.2

Updated for the changes in Eclipse 4.1.15 because there is a breaking change in the smart lm loader

Sourcecivitai.com/models/2736470
TaskMultiCapabilitiesCaptioning · Object detection · Text generation · Text to videoVersionRelease 3122307 — detectionImageTo_v22.jsonEstimated VRAMNot yet characterizedBgrade

Runtime profile

Access
External workflow
Status
Listed
Version
detectionImageTo_v22.json
Source
Civitai
Updated
Oct 18, 2026

What you need

Model files
0 GiB

Remaining hardware or download-size estimates are not available yet.

Requirements

Node packs

1

AI-generated commentary

AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.

Purpose

  • Detection / Image to Prompt — v2.2 is for turning single images, image folders, or video frames into image prompts, tags, object detections, segmentation masks, and bounding-box results, with additional tools for timeline prompts, prompt variations, song lyrics, and interactive چ

Flow

  • Choose single-image mode or folder/video mode, then optionally use Image Selector to choose the images or frames to process.

  • The selected image is shared with Detection, Image to Prompt, and Timeline Prompts through Set/Get named channels, so groups can be muted without breaking the visible wiring.

Inputs and outputs

  • Detection accepts a text query such as “face, hair” and can show isolated regions, binary masks, bounding-box text, and OCR output.

  • Image to Prompt can return detailed descriptions and comma-separated tags; Timeline Prompts can return structured timelines for Wan2.1 and LTX-Video.

  • Text-only modes can expand a seed prompt into three variations, compose song lyrics or poetry from a theme, and return direct chat responses.

Setup

  • Configure Hugging Face, GGUF, or Ollama credentials in config.json when using Docker-based backends; local GGUF and Transformers backends use models in models/llms/ or models/text_encoders/.

    Suggestion · not verified

Dependencies

  • Requires the ComfyUI_Eclipse node pack, which provides the smart loaders, Smart Detection, image loading and selection, Set/Get routing, and preview nodes used here.

Configuration

  • Smart LM Loader offers Transformers, GGUF, Ollama, llama.cpp, vLLM (Docker), vLLM (Native), SGLang (Docker), and WD14 Tagger backends.

  • Add custom model entries under the transformers, gguf, or ollama keys in registry/user_models.json; names beginning with an underscore are ignored.

    Suggestion · not verified

  • For batch tagging, set Folder Mode, enter the folder path, and either bypass Image Selector for automatic processing or leave it active to choose files.

    Suggestion · not verified

Cautions

  • The guide says this version was updated for Eclipse 4.1.15 because of a breaking change in Smart LM Loader; verify your installed Eclipse version before use.

    Suggestion · not verified

  • The two parallel Image-to-Prompt loader nodes are described as a showcase setup; the guide says captioning and tag generation can instead run sequentially in one loader’s multi-task system.

    Suggestion · not verified

Does this need to be edited?

Sign in to send an edit request.

Sources

1 source
CivitaiPrimaryVersion 3122307
civitai.com/models/2736470

Verified Oct 18

Source excerpts

3 excerpts
NoteOct 18civitai.com/models/2736470

Source context: 357 downloads · Type Workflows · Base model Other

NoteAug 7civitai.com/models/2736470

Source context: 204 downloads · Type Workflows · Base model Other

NoteJul 28civitai.com/models/2736470

Source context: 150 downloads · Type Workflows · Base model Other