Where do I put the Qwen2.5-VL text encoder file?

Place qwen_2.5_vl_fp16.safetensors in ComfyUI/models/text_encoders. If you’re using the repackaged OmniGen2 weights from Hugging Face, follow their folder structure and naming exactly.

How do I control image size and aspect ratio?

Set width and height in the OmniGen2 node. Common pairs are 1024x1024 (square), 1344x768 (16:9), or 832x1216 (2:3). Higher resolutions require more VRAM, so increase gradually.

How can I get repeatable results?

Use a fixed seed value in the OmniGen2 node. To explore variations, either change the seed slightly or enable batch/count to generate multiple outputs in one pass.

Does OmniGen2 support negative prompts?

If your OmniGen2 node exposes a negative_prompt input, use it to steer away from undesired elements. If not, phrase constraints directly in your prompt (e.g., “no text, minimal background, without watermark”).

OmniGen2: Text to Image - ComfyUI Workflow

This workflow demonstrates a minimal, fast path from text prompt to finished image using OmniGen2’s unified 7B multimodal model. A single OmniGen2 node (custom node id 4b17d220-4312-4981-9eae-9a76bf3b6ec9) ingests your prompt, encodes it with the Qwen2.5-VL text encoder, and produces a high-quality image without the complexity of diffusion samplers or long node chains. The output is then passed to SaveImage for consistent file naming and export, while a MarkdownNote provides in-canvas guidance and links to the official docs.

Technically, the prompt is embedded via the qwen_2.5_vl_fp16.safetensors text encoder and routed through OmniGen2’s dual-path architecture, which unifies language understanding with image generation in a single model. The node exposes practical controls—such as resolution, seed, and batch/count—so you can tune aspect ratio and reproducibility. The entire setup can be wrapped as a Subgraph for a clean UI: expand it any time to reveal advanced parameters and adjust defaults. This makes the workflow ideal for quick iteration, predictable outputs, and easy handoff to teammates.

API

Use this workflow from code

Every Comfy workflow is a JSON graph. The payload below is this workflow, exactly as ComfyUI runs it — fetch it from the URL, keep it in version control, or load it in ComfyUI and run it node by node.

image_omnigen2_t2i.json

Fetching workflow JSON…

Run it from TypeScript or Python with the Comfy SDK. The same code targets Comfy Cloud or a ComfyUI you host yourself — only the base URL changes.

// Install (beta)
npm i @comfyorg/sdk

// Run "OmniGen2: Text to Image" (TypeScript)
import { Comfy } from "@comfyorg/sdk";

const client = new Comfy({ apiKey: "comfyui-..." });

// This workflow, exported in API format (see note below)
const wf = await client.workflows.fromFile("image_omnigen2_t2i_api.json");

const job = await client.run(wf);
await job.getOutputs("9")[0].toFile("output.png");  // SaveImage

The SDK takes a workflow in API format: open this workflow in ComfyUI and use File → Export Workflow (API).

Comfy Cloud API access requires a plan with an API key.

SDK docs Get an API key

FAQ

Frequently Asked Questions