Generate new images with Flux.1 dev conditioned by two Flux Redux visual references. For a first run, upload both images, replace the example prompt with your intended scene, and keep reference strengths at 1, output size at 1024 × 1024, image count at 1, and sampling steps at 20. Clear the prompt if you want to omit descriptive text; both reference uploads remain required, even when a reference strength is zero.
Workflow details
Runtime profile
Sources
1 sourceHover nodes for Pipe controls
Core
Primary Pipe surface
Reference image 1
LoadImage
Reference image 2
LoadImage
Positive prompt
CLIPTextEncode
Output size
EmptySD3LatentImage
Reference 1 influence
StyleModelApply
Reference 2 influence
StyleModelApply
Extended
Additional surfaced controls
Reference 1 framing
CLIPVisionEncode
Reference 2 framing
CLIPVisionEncode
Guidance
FluxGuidance
Seed
RandomNoise
Sampling
BasicScheduler
Sampler
KSamplerSelect
Sampling calibration
ModelSamplingFlux
Remaining hardware or download-size estimates are not available yet.
Requirements
VAE · Hugging Face · Comfy-Org/Lumina_Image_2.0_Repackaged · Lumina Image 2.0 Repackaged
Text encoder · Hugging Face · comfyanonymous/flux_text_encoders · Flux Text Encoders
Checkpoint · Hugging Face · Comfy-Org/flux1-dev
Checkpoint · Hugging Face · Comfy-Org/Flux1-Redux-Dev
sigclip_vision_patch14_384.safetensors
File unverifiedVision model · Hugging Face · Comfy-Org/sigclip_vision_384 · Sigclip Vision 384
Text encoder · Hugging Face · comfyanonymous/flux_text_encoders · Flux Text Encoders
Node pack · GitHub · tea-time-labs/sweet-tea-nodes