Model
Trends
.ai
Model
Trends
.ai
les meilleurs modèles d'IA open source

Nœud EmptySD3LatentImage dans ComfyUI

EmptySD3LatentImage creates the 16-channel empty latent that Flux, SD3 and SD3.5 need; it replaces Empty Latent Image in those workflows.
Pack de nœuds : ComfyUI core
Catégorie : Latent
Cette page n'est pas encore traduite ; elle est affichée en anglais.

Ce que fait EmptySD3LatentImage

SD3 and Flux use a VAE with 16 latent channels instead of the 4 channels of SD 1.5 and SDXL. A standard Empty Latent Image hands the sampler the wrong shape, which ends in noise or a size error. EmptySD3LatentImage produces the right tensor and otherwise behaves the same: width, height and batch_size in pixels.
Flux handles a wide range of sizes well, from 512 up to about 2 megapixels in one pass (1024x1024, 1152x896, 1344x768, 1536x1024). SD3.5 prefers 1024-class sizes.

Entrées

Nom
Type
Rôle
width
INT
Image width in pixels, multiple of 16 recommended.
height
INT
Image height in pixels.
batch_size
INT
Images per run.

Sorties

Nom
Type
Rôle
LATENT
LATENT
The empty 16-channel latent for KSampler.
AD
Oubliez l'installation : des workflows ComfyUI préinstallés sur le cloud
BitVector exécute des workflows ComfyUI prêts à l'emploi sur ses propres GPU. Rien à installer, aucun nœud manquant, aucune case rouge. Ouvrez-le sur votre téléphone ou votre portable et générez en une minute.

Comment utiliser EmptySD3LatentImage

  1. Add EmptySD3LatentImage instead of Empty Latent Image.
  2. Set 1024x1024 (or another Flux size).
  3. Connect to KSampler latent_image, denoise 1.0.

Réglages et conseils

  • Flux Dev makes good 1536x1024 images directly; no hires pass needed for many uses.
  • Multiples of 16 avoid edge artifacts with Flux.
  • Qwen-Image and HiDream also use this node.

Dépannage de EmptySD3LatentImage

Flux output is noise although everything else is right

Pourquoi cela arrive
A 4-channel Empty Latent Image is wired into the sampler.

Comment le corriger
Swap it for EmptySD3LatentImage.

RuntimeError about channel sizes (expected 16, got 4)

Pourquoi cela arrive
Same cause: the latent has the wrong channel count for the model.

Comment le corriger
Use this node for Flux/SD3 and Empty Latent Image for SD 1.5/SDXL; also check that the VAE Encode in img2img uses the Flux VAE.

AD
Lancez ce workflow depuis votre téléphone
Chaque workflow de cette page est préinstallé sur BitVector, modèles et nœuds personnalisés déjà en place. Choisissez-en un, tapez un prompt, c'est fait. Zéro configuration, rien à télécharger.

Questions sur EmptySD3LatentImage

Does it work for Flux Schnell?

Yes, every Flux variant uses it.

Can I use it for SDXL?

No, SDXL needs the 4-channel Empty Latent Image.

Nœuds liés

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 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.
Flux Guidance
ComfyUI core
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.
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.
AD
Marre de réparer des nœuds ? Laissez faire le cloud
BitVector garde des centaines de workflows ComfyUI installés, à jour et testés sur des GPU cloud rapides. Pas de Python, pas d'erreurs CUDA, pas de limite de VRAM. Depuis n'importe quel navigateur.

Autres nœuds ComfyUI

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.
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.
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.