Sign inGet started
Model · Civitai

pretty_pixels/GGUF: HyperFlux 8-Steps (Flux.1 Dev + ByteDance HyperSD LoRA)

[Note: Unzip the download to get the GGUF. Civit doesn't support it natively, hence this workaround] A merge of Flux.D with the 8-step HyperSD LoRA from ByteDance - turned into GGUF. As a result, you get an ultra-memory efficient and fast DEV (CFG sensitive) model that generates fully denoised images with just 8 steps while consuming ~6.2 GB VRAM (for the Q4_0 quant). It can be used in ComfyUI with this custom node or with Forge UI. See https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/1050 to learn more about Forge UI GGUF support and also where to download the VAE, clip_

Author / organizationpretty_pixels
Downloads7.1K (as reported by Civitai)
Likes242
Tasktext-to-image
Created3 September 2024
Last updated at source—
text-to-imagecheckpointflux.1 dhypersdbase models8stepsbase modelflux1.dgguf
Embed this entry
<iframe src="https://silytics.si/embed/item/84e7eb73-a5fe-4595-8a34-9559cc4d7164" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

Popularity, last 2 days

7,086 now (+2 since 2026-10-15). Counts as reported by the source, snapshotted daily by Silytics.

More from pretty_pixels

Silytics shows public metadata from Civitai and links to the original. Information may be incomplete or out of date. Last refreshed 16 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.