Preview Image node in ComfyUI
Preview Image displays an IMAGE inside the node without saving it to the output folder (a temporary file is kept until restart), ideal for checking intermediate steps like masks, ControlNet maps and hires passes.
Node pack: ComfyUI core
Category: Image
What Preview Image does
Preview Image is Save Image without the permanent file. The picture is written to ComfyUI/temp with a random prefix, shown in the node and dropped on the next restart. Use it anywhere you want to see what a branch of the graph produces: the output of a Canny preprocessor, a mask converted to an image, the result before and after an upscale.
Because it is an output node, connecting it also forces that part of the graph to execute. That makes it a handy debugging tool: attach a Preview Image to a tensor and the node will run even if nothing downstream uses it.
Inputs
Name | Type | What it is |
|---|---|---|
images | IMAGE | The pictures to display. |
Outputs
Name | Type | What it is |
|---|---|---|
(none) | - | Output node: displays the pictures and keeps a temporary copy. |
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 Preview Image
- Connect any IMAGE to a Preview Image node.
- Queue the prompt and inspect the result in the node.
- Right-click a preview to save it, open it in a new tab or send it to Load Image.
- Replace it with Save Image when you are happy with the result.
Settings and tips
- Convert Mask to Image -> Preview Image is the fastest way to inspect a mask.
- Previews count as outputs in the history, so you can retrieve them until the server restarts.
- Many previews of 4K images slow the browser; preview downscaled copies for big batches.
- --preview-method auto in the start command also shows live sampling previews in KSampler.
Troubleshooting Preview Image
Preview disappeared after restart
Why it happens
Temporary files are cleared when ComfyUI starts.
How to fix it
Use Save Image for anything you want to keep.
The graph runs even though the preview is not connected to the sampler
Why it happens
Preview Image is an output node; every output node and its dependencies run on each queue.
How to fix it
Bypass the node (Ctrl+B) or delete it when you do not need that branch.
Preview shows a black square
Why it happens
The tensor is not an IMAGE in the 0-1 range, for example a MASK or latent connected by mistake.
How to fix it
Decode latents with VAE Decode and convert masks with Convert Mask to Image first.
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 Preview Image
Is there a difference in quality between Preview and Save?
No, both write 8-bit PNG. Only the location and the lifetime differ.
Can I preview latents?
Not directly; add a VAE Decode (or the Preview from the Taesd fast decoder) before the preview.
Related nodes
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.
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.
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.
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.
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 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