Flux 2 Dev with optional image references
Generate new images from text with Flux 2 Dev, optionally conditioned by one or two reference images.
Loading this version’s controls and setup…
Workflow details
Workflow details
Runtime profile
- Publisher
- Sweet Tea Automation
- Status
- Listed
- Version
- v0.1.1
- Updated
- Nov 2, 2026
Hover nodes for Pipe controls
Core
Primary Pipe surface
Reference image 1
LoadImage
Reference image 2
LoadImage
Positive prompt
CLIPTextEncode
Output size
EmptyFlux2LatentImage
Use reference 1
ReferenceLatent
Use reference 2
ReferenceLatent
Extended
Additional surfaced controls
Guidance
FluxGuidance
Randomization
RandomNoise
Sampling
Flux2Scheduler
Sampler
KSamplerSelect
Reference 1 preparation
ImageScaleToTotalPixels
Reference 2 preparation
ImageScaleToTotalPixels
What you need
- Model files
- 49.8 GiB known subtotal
Remaining hardware or download-size estimates are not available yet.
Output
- Generated images · image
Requirements
Models
3Diffusion model · 33.0 GB · SAFETENSORS · FP8 (unverified) · Unknown
flux2-vae.safetensors
Repository matchedVAE · Unknown
Text encoder · 16.8 GB · SAFETENSORS · FP8 (unverified) · Unknown
Node packs
2SweetTeaPreviewImage
FoundNode pack · Unknown
Node pack · GitHub · tea-time-labs/sweet-tea-nodes
Sources
1 source
Sources
1 sourceModel artifacts
1 artifact
Model artifacts
1 artifact8c830b48-e8c6-49a7-bb33-2b1d0eadcc87-catalog-workflow-463d3926de930607b04a926d4a13ecac6acee26031d199792c36d969f4134dd-0.1.1.tea
tea · 21.9 KB · SHA-256 8847fdbd1e05…60b2
Download file