ByteDance / text-to-image updated 1 year ago

Hyper-SD

Name: Hyper-SD
Author: ByteDance

Aug.26, 2024. 💥💥💥 Our 8-steps and 16-steps FLUX.1-dev-related LoRAs are available now! We recommend LoRA scales around 0.125 that is adaptive with training and guidance scale could be kept on 3.5. Lower step LoRAs would be coming soon. 💥💥💥 Aug.19, 2024. SD3-related CFG LoRAs are available now! We recommend setting guidance scale to 3.0/5.0/7.0 at 4/8/16-steps. Don't forget to fuse lora with a relatively small s...

Params

—

Context

—

Downloads 30d

47 K

Likes

1,345

Licence: unknown Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 10 days

47 K41 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	fp16	27.7 GB	31.0 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

First seen on the Hub: 2024-04-20
Base model: FLUX.1-dev
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

Base model and the most-downloaded derivatives in the catalog.

Base FLUX.1-dev black-forest-labs 547 K

Compare with

stable-diffusion-v1-5 1.6 M stable-diffusion-xl-base-1.0 1.5 M sdxl-turbo 1.1 M Z-Image-Turbo 1.1 M dreamshaper-7 895 K Flux2-Klein-9B-True-V2 792 K

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB