Loading
Tem um workflow do ComfyUI? Gere uma documentação legível direto no navegador.Torne um workflow legível.Experimentar agora ↗
Generate images from a text prompt using the fixed FLUX.2 dev model, with an optional Turbo LoRA mode. No source image is required, and there is no negative prompt input.
Workflow details
Perfil de execução
Fontes
1 fonteHover nodes for Pipe controls
Core
Primary Pipe surface
Positive prompt
CLIPTextEncode
Output size
EmptyFlux2LatentImage
Scheduler size
Flux2Scheduler
Turbo mode
PrimitiveBoolean
Extended
Additional surfaced controls
Prompt guidance
FluxGuidance
Seed
RandomNoise
Standard sampling
PrimitiveInt
Turbo sampling
PrimitiveInt
Turbo strength
LoraLoaderModelOnly
Sampling
KSamplerSelect
Remaining hardware or download-size estimates are not available yet.
Requisitos
Flux_2-Turbo-LoRA_comfyui.safetensors
Não resolvidoLoRA · Hugging Face · ByteZSzn/Flux.2-Turbo-ComfyUI
flux2_dev_fp8mixed.safetensors
Arquivo não verificadoCheckpoint · Hugging Face · Comfy-Org/flux2-dev
full_encoder_small_decoder.safetensors
Arquivo não verificadoVAE · Hugging Face · black-forest-labs/FLUX.2-small-decoder · FLUX.2 Small Decoder
mistral_3_small_flux2_bf16.safetensors
Arquivo não verificadoText encoder · Hugging Face · Comfy-Org/flux2-dev
Pacote de nós · GitHub · tea-time-labs/sweet-tea-nodes
