Generate edited images from an uploaded reference and written instructions using FLUX.2, with standard and Turbo modes.
Workflow details
Runtime profile
Sources
1 sourceHover nodes for Pipe controls
Core
Primary Pipe surface
Source image
LoadImage
Edit instructions
CLIPTextEncode
Output size
ImageScaleToTotalPixels
Image count
EmptyFlux2LatentImage
Turbo mode
PrimitiveBoolean
Extended
Additional surfaced controls
Prompt guidance
FluxGuidance
Seed
RandomNoise
Standard sampling
PrimitiveInt
Turbo sampling
PrimitiveInt
Turbo LoRA
LoraLoaderModelOnly
Sampler
KSamplerSelect
Remaining hardware or download-size estimates are not available yet.
Requirements
Flux_2-Turbo-LoRA_comfyui.safetensors
Not resolvedLoRA · Hugging Face · ByteZSzn/Flux.2-Turbo-ComfyUI
flux2_dev_fp8mixed.safetensors
File unverifiedCheckpoint · Hugging Face · Comfy-Org/flux2-dev
full_encoder_small_decoder.safetensors
File unverifiedVAE · Hugging Face · black-forest-labs/FLUX.2-small-decoder · FLUX.2 Small Decoder
mistral_3_small_flux2_bf16.safetensors
File unverifiedText encoder · Hugging Face · Comfy-Org/flux2-dev
Node pack · GitHub · tea-time-labs/sweet-tea-nodes