Tiny AutoEncoder Previews
While a model denoises, InvokeAI shows a preview of the image after each step. By default the preview is a linear projection of the latents: one pixel per latent, upscaled, so it is blurry and its colours are approximate. A Tiny AutoEncoder (TAE) is a small decoder by madebyollin (MIT license) that turns the same latents into a preview close to the final image, in about 25 ms on an RTX 4090. It needs a GPU: on CPU-only installs it is not recommended (see Cost and fallback).
TAE previews change only what you see while a generation runs. The finished image is decoded by the model’s VAE as always and is identical with the setting on or off.
Enabling TAE previews
Section titled “Enabling TAE previews”-
Set the option in
invokeai.yaml, then restart InvokeAI:tiny_autoencoder_previews: trueIt is a server setting and is off by default. See All Settings.
-
In Model Manager → Starter Models, install the Tiny AutoEncoder for the families you generate with (search for preview decoder). Each one is 5 to 31 MB.
| Starter model | Previews for |
|---|---|
| TAESD (SD 1.x/2.x preview decoder) | SD 1.x, SD 2.x |
| TAESDXL (SDXL preview decoder) | SDXL, SDXL Refiner |
| TAESD3 (SD3 preview decoder) | SD 3 |
| TAEF1 (FLUX.1 preview decoder) | FLUX.1, Z-Image |
| TAEF2 (FLUX.2 preview decoder) | FLUX.2, FLUX.3, ERNIE-Image |
| TAEQI2.1 (Qwen-Image-2.1 preview decoder) | Qwen-Image-2.1 |
A TAE serves every family that denoises in its latent space, so you need only one per row. To install a TAE file you already have, see Preview decoders for the files InvokeAI accepts.
FLUX.1, FLUX.2, FLUX.3 and ERNIE-Image preview the image the model predicts, so the preview is clean from the first step. Z-Image, SD 3 and Qwen-Image-2.1 preview the current noisy latent: early previews show sharp noise, which clears as denoising proceeds. SD 1.x/2.x and SDXL depend on the scheduler: DDIM, DDPM, Euler, Euler a, Heun, LMS, KDPM2, KDPM2 a and DPM++ SDE report their prediction and preview cleanly; DPM++ 2M, 2M SDE, 3M and 2S, UniPC, DEIS, PNDM, LCM, TCD and ER-SDE preview the noisy latent.
All other families keep the linear preview: Qwen-Image, Qwen-Image Edit, Krea-2, Anima, CogView4, Ideogram 4, Wan 2.2 and LTX-2. MiniMax H3 previews with its own built-in decoder whatever this setting says.
Cost and fallback
Section titled “Cost and fallback”Only the preview frames that are actually sent to the UI are decoded, between two denoising steps. Previews are at most 1024 pixels on their long edge; larger generations are previewed at reduced resolution and shown at full size. At that size, on an RTX 4090, a preview takes about 25 ms and about 0.65 GB of VRAM while it decodes (about 0.16 GB for Qwen-Image-2.1). Without a GPU a preview takes about 2 seconds, so TAE previews are not recommended on CPU-only installs.
InvokeAI spaces TAE preview frames so that previews cost at most about a tenth of the denoising time. On fast models the preview therefore updates a few times per second rather than after every step. In practice the cost is lower: on an RTX 4090, denoising a 1024×1024 SDXL image in 30 steps took about 4.44 s with TAE previews against 4.18 s without, roughly 6% more.
InvokeAI falls back to the linear preview by itself, and the generation always continues:
- No matching TAE installed: linear previews. The server log names the family once.
- The TAE does not fit in VRAM next to the running model: linear previews for that generation, noted once in the server log. This is the case whenever the main model is only partially loaded into VRAM, as on low-VRAM cards.
- Loading or decoding the TAE fails: a warning with the error in the server log, once per kind of failure, then linear previews for the rest of that generation.