Model
Trends
.ai
Model
Trends
.ai
cele mai bune modele AI open source

Nodul Flux Guidance în ComfyUI

Flux Guidance (FluxGuidance) writes the guidance value into the conditioning that Flux Dev was distilled to expect, replacing cfg; 3.5 is the default and 2 to 5 the useful range.
Pachet de noduri: ComfyUI core
Categorie: Conditioning și prompturi
Această pagină nu a fost încă tradusă, așa că este afișată în engleză.

Ce face Flux Guidance

Flux Dev is a guidance-distilled model: instead of running the prompt twice per step like classic CFG, it reads a single guidance number from the conditioning. Flux Guidance sets that number. The sampler cfg should stay at 1.0, which means no classic CFG and no negative prompt cost.
Lower guidance (1.5-2.5) gives softer, more photographic and more varied images; higher values (4-6) follow the prompt harder with more contrast and the typical plasticky Flux look. Flux Schnell ignores the value, and Flux Kontext and Flux Fill also use it.

Intrări

Nume
Tip
Ce este
conditioning
CONDITIONING
The encoded positive prompt from CLIP Text Encode.
guidance
FLOAT
The distilled guidance strength. 3.5 default, 2-5 typical.

Ieșiri

Nume
Tip
Ce este
CONDITIONING
CONDITIONING
The prompt with guidance embedded, for the sampler positive input.
AD
Sari peste configurare: fluxuri ComfyUI preinstalate în cloud
BitVector rulează fluxuri de lucru ComfyUI gata făcute pe propriile GPU-uri. Fără instalare, fără noduri lipsă, fără casete roșii. Deschide-l pe telefon sau laptop și generează într-un minut.

Cum folosești Flux Guidance

  1. Encode the prompt with CLIP Text Encode (CLIP from DualCLIPLoader).
  2. Pass the CONDITIONING through Flux Guidance.
  3. Connect the result to KSampler positive; set KSampler cfg to 1.0.
  4. For the negative input, use ConditioningZeroOut of the same prompt or an empty prompt.

Setări și sfaturi

  • For realism try guidance 2.0-2.5 with 25-30 steps; for illustration and text rendering 3.5-4.5.
  • Guidance above 6 gives burnt skin and oversharpening.
  • If you want a real negative prompt on Flux, raise cfg to 1.5-2 and expect roughly double the time per step.
  • Flux Kontext editing usually works best near 2.5-3.0.

Depanare Flux Guidance

Flux images are washed out and blurry

De ce se întâmplă
No Flux Guidance node in the chain, so the model runs at an effective guidance of 1, or cfg is also 1 with no guidance embedded.

Cum se repară
Add Flux Guidance between the prompt and the sampler, set it to 3.5.

Images look plastic, oversaturated or have grid artifacts

De ce se întâmplă
Guidance is too high, or classic cfg above 1 is combined with distilled guidance.

Cum se repară
Keep cfg at 1.0 and lower guidance to 2.5-3.5.

The value does nothing on Flux Schnell

De ce se întâmplă
Schnell is a timestep-distilled model that does not read the guidance value.

Cum se repară
Expected. Use Flux Dev when you need guidance control.

AD
Rulează acest flux de lucru de pe telefon
Fiecare flux de lucru de pe această pagină este preinstalat pe BitVector cu modelele și nodurile personalizate deja la locul lor. Alege unul, tastează un prompt, gata. Zero configurare, nimic de descărcat.

Întrebări despre Flux Guidance

Should cfg be 1.0 with Flux?

Yes, for Dev and Schnell. The guidance number replaces it.

Does Flux Guidance apply to the negative prompt?

No, only to the positive conditioning. The negative is normally ignored at cfg 1.

Noduri conexe

Load Diffusion Model
ComfyUI core
Load Diffusion Model (UNETLoader) loads a bare denoising network such as Flux, SD3.5, Wan or HunyuanVideo from models/diffusion_models, with a weight_dtype option for fp8 to save VRAM.
DualCLIPLoader
ComfyUI core
DualCLIPLoader loads two text encoders at once, for example clip_l plus t5xxl for Flux or clip_g plus t5xxl for SD3, and outputs one CLIP object for the prompt nodes.
CLIP Text Encode (Prompt)
ComfyUI core
CLIP Text Encode turns a text prompt into CONDITIONING using the model text encoder. One node holds the positive prompt, a second one the negative prompt.
KSampler
ComfyUI core
KSampler runs the denoising loop: it takes the model, prompts and a latent and produces the finished latent image, controlled by seed, steps, cfg, sampler, scheduler and denoise.
EmptySD3LatentImage
ComfyUI core
EmptySD3LatentImage creates the 16-channel empty latent that Flux, SD3 and SD3.5 need; it replaces Empty Latent Image in those workflows.
AD
Sătul să repari noduri? Lasă cloud-ul să o facă
BitVector menține sute de fluxuri ComfyUI instalate, actualizate și testate pe GPU-uri cloud rapide. Fără Python, fără erori CUDA, fără limite de VRAM. Funcționează din orice browser.

Mai multe noduri ComfyUI

ComfyUI Manager
ComfyUI-Manager
ComfyUI Manager is the extension that installs, updates and fixes custom node packs and models from inside the interface, resolves missing nodes in imported workflows and snapshots your setup.
Load Checkpoint
ComfyUI core
Load Checkpoint (CheckpointLoaderSimple) opens a .safetensors or .ckpt model file and hands out the three parts every workflow needs: the diffusion MODEL, the CLIP text encoder and the VAE.
Save Image
ComfyUI core
Save Image writes the IMAGE tensor to ComfyUI/output as a PNG, with the whole workflow embedded in the file metadata so the picture can be dragged back into ComfyUI to restore the graph.
VAE Decode
ComfyUI core
VAE Decode converts the sampled LATENT into a pixel IMAGE with the VAE; VAE Decode (Tiled) does the same in tiles for very large images.
Empty Latent Image
ComfyUI core
Empty Latent Image creates the blank latent canvas (width, height, batch_size) that text-to-image sampling starts from; dimensions must be multiples of 8 and match the model family.
Load Image
ComfyUI core
Load Image reads a picture from the ComfyUI input folder (or an upload) and outputs an IMAGE tensor plus a MASK taken from the alpha channel, the starting point for img2img, inpainting, ControlNet and IP-Adapter graphs.