Lens Turbo text to image
Generate images from a written description with the fixed Lens Turbo model, GPT-OSS text encoder and FLUX.2 VAE. No uploaded image is required.
Workflow details
Workflow details
Runtime profile
- Publisher
- Sweet Tea Automation
- Status
- Listed
- Version
- Checking published version…
- Updated
- Oct 25, 2026
Hover nodes for Pipe controls
Core
Primary Pipe surface
Positive prompt
CLIPTextEncode
Output size
ResolutionSelector
Image count
EmptyLatentImage
Extended
Additional surfaced controls
Negative prompt
CLIPTextEncode
Sampling
SamplerCustom
Sampling schedule
BasicScheduler
Sampler
KSamplerSelect
Guidance normalization
CFGNorm
Resolution-dependent sampling
ModelSamplingFlux
What you need
Hardware and download-size estimates are not available yet.
Guides for this recipe
Output
- Generated images · image
Requirements
Models
3- File unverified
VAE · Hugging Face · Comfy-Org/Lens
- File unverified
Text encoder · Hugging Face · Comfy-Org/Lens
- File unverified
Checkpoint · Hugging Face · Comfy-Org/Lens
Node packs
1Node pack · GitHub · tea-time-labs/sweet-tea-nodes
Sources
1 source
Sources
1 source