OmniGen2: Text to Image
Generate a single image or a batch from text with OmniGen2. No uploaded image is required; the diffusion model, Qwen text encoder, and VAE are fixed by this workflow.
Workflow details
Workflow details
Runtime profile
- Publisher
- Sweet Tea Automation
- Status
- Listed
- Version
- Checking published version…
- Updated
- Oct 26, 2026
Hover nodes for Pipe controls
Core
Primary Pipe surface
Positive prompt
CLIPTextEncode
Negative prompt
CLIPTextEncode
Output size
EmptySD3LatentImage
Extended
Additional surfaced controls
Guidance
DualCFGGuider
Seed
RandomNoise
Sampling
BasicScheduler
Sampler
KSamplerSelect
What you need
- Model files
- 0.3 GiB known subtotal
Remaining hardware or download-size estimates are not available yet.
Output
- Generated images · image
Requirements
Models
3- File unverified
VAE · Hugging Face · Comfy-Org/Lumina_Image_2.0_Repackaged
- File unverified
Checkpoint · Hugging Face · Comfy-Org/Omnigen2_ComfyUI_repackaged
- File unverified
Text encoder · Hugging Face · Comfy-Org/Omnigen2_ComfyUI_repackaged
Node packs
1Node pack · GitHub · tea-time-labs/sweet-tea-nodes
Sources
1 source
Sources
1 source