xinsir / text-to-image updated 2 years ago

controlnet-union-sdxl-1.0

- Use bucket training like novelai, can generate high resolutions images of any aspect ratio - Use large amount of high quality data(over 10000000 images), the dataset covers a diversity of situation - Use re-captioned prompt like DALLE.3, use CogVLM to generate detailed description, good prompt following ability - Use many useful tricks during training. Including but not limited to date augmentation, mutiple loss, m...

Params
1.3 B
Context
Downloads 30d
100 K
Likes
1,803
Commercial use: allowed apache-2.0 Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 10 days
104 K98 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.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
model.safetensors f16 5.0 GB 6.2 GB ✅ Runs comfortably
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Parameters
1.3 B
Tensor type
F16
Licence
apache-2.0
First seen on the Hub
2024-07-07
Training datasets
undisclosed
Added to our catalog
2026-07-28