Empty Latent Image node in ComfyUI
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.
Node pack: ComfyUI core
Category: Latent
What Empty Latent Image does
Text-to-image needs a starting point. Empty Latent Image produces a latent tensor filled with zeros at the requested size, and KSampler adds the noise. Latent space is 8 times smaller than pixels for SD models, so a 1024x1024 image is a 128x128 latent; the node takes pixel sizes and divides for you.
Pick sizes the model was trained on: 512x512 or 512x768 for SD 1.5, 1024x1024 / 832x1216 / 1216x832 for SDXL, Pony and Illustrious. Larger first-pass sizes cause duplicated subjects; use a hires pass for more pixels. For Flux, SD3 and video models use EmptySD3LatentImage or the family-specific latent node, which has a different channel count.
Inputs
Name | Type | What it is |
|---|---|---|
width | INT | Image width in pixels, multiple of 8 (64 recommended). |
height | INT | Image height in pixels, multiple of 8. |
batch_size | INT | How many images to make in one run with consecutive seeds. |
Outputs
Name | Type | What it is |
|---|---|---|
LATENT | LATENT | The empty latent for KSampler latent_image. |
AD
Skip the setup: ComfyUI workflows preinstalled on the cloud
BitVector runs ready-made ComfyUI workflows on its own GPUs. No install, no missing nodes, no red boxes. Open it on your phone or laptop and generate in a minute.
How to use Empty Latent Image
- Add Empty Latent Image.
- Set width and height for the model family (1024x1024 for SDXL).
- Set batch_size 1 while testing, higher once the prompt works.
- Connect LATENT to KSampler latent_image and keep denoise at 1.0.
Settings and tips
- SDXL sweet spots: 1024x1024, 896x1152, 832x1216, 1152x896, 1216x832, 1344x768.
- SD 1.5 above 768 on the long side tends to double heads and bodies; upscale afterwards instead.
- batch_size 4 is a cheap way to explore seeds; VRAM scales with it.
- Width and height that are not multiples of 8 are rounded down.
Troubleshooting Empty Latent Image
Flux / SD3 / Wan produce garbage with this node
Why it happens
Those models use 16-channel latents; Empty Latent Image makes the 4-channel SD latent.
How to fix it
Replace it with EmptySD3LatentImage (Flux, SD3, Qwen) or the Wan / Hunyuan empty video latent nodes.
Two heads, duplicated people or tiling patterns
Why it happens
The canvas is much larger than the training resolution, so the model composes several images in one.
How to fix it
Generate at the native size and upscale with a latent or pixel hires pass.
Error: height and width must be divisible by 8
Why it happens
A size like 1000x700 was entered.
How to fix it
Use multiples of 8, ideally 64 (1024, 960, 896, 832, 768).
Out of memory with a batch
Why it happens
batch_size multiplies the memory the sampler needs.
How to fix it
Lower batch_size and queue several runs instead.
AD
Run this workflow from your phone
Every workflow on this page is preinstalled on BitVector with the models and custom nodes already in place. Pick one, type a prompt, done. Zero setup, nothing to download.
Questions about Empty Latent Image
Can I make non-square images?
Yes, any aspect ratio within the model comfort zone. Keep the pixel count near the training size.
What does batch_size do to the seed?
Each image in the batch uses the base seed plus its index.
Related nodes
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.
Upscale Latent and Upscale Latent By
ComfyUI core
Upscale Latent resizes a latent to a new size (or by a factor) so a second KSampler can add detail at higher resolution: the classic hires fix.
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.
AD
Tired of fixing nodes? Let the cloud do it
BitVector keeps hundreds of ComfyUI workflows installed, updated and tested on fast cloud GPUs. No Python, no CUDA errors, no VRAM limits. Works from any browser.
More ComfyUI 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.
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.
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.
Load LoRA
ComfyUI core
Load LoRA (LoraLoader) applies a LoRA file to the MODEL and CLIP with separate strengths, so a style, character or concept can be added to any checkpoint without merging.
Model
Trends
.ai
© ModelTrends.ai
|
Made in Japan
|
© 2026