Downloads · 30 days
11
10% of all-time downloads
qwen-calibri
v-gen-ai/qwen-calibri
qwen-calibri is a text-to-image model from v-gen-ai. Use it when you need an image from a text prompt. It is set up for diffusers.
Paper: Calibri: Enhancing Diffusion Transformers via Parameter-Efficient Calibration
All-time downloads
105
Public
Parameters
20.4B
57.7 GB on disk
Likes
2
Public
Repo makeup
Click a slice to open those files.
.safetensors57.7 GB · 100%
At a glance
- Task
- Text-to-Image
- Library
- diffusers
- Access
- Public
- Created
- Mar 26, 2026
- Updated
- Mar 27, 2026
- SHA
- 546317fe
Model card
From the Hugging Face model README
Paper: Calibri: Enhancing Diffusion Transformers via Parameter-Efficient Calibration
Calibri Qwen Image
Guide to run:
import torch
from diffusers import DiffusionPipeline
pipe = DiffusionPipeline.from_pretrained(
"makriot/qwen-calibri",
custom_pipeline="makriot/qwen-calibri",
torch_dtype=torch.bfloat16,
trust_remote_code=True
)
pipe.to("cuda")
image = pipe(
prompt="A futuristic cityscape",
true_cfg_scale=4.0,
num_inference_steps=15,
height=512,
width=512,
).images[0]
Model was trained with resolution 512 x 512, but it is possible to run with other resolutions.
- Task
- Text-to-Image
- Library
- diffusers
- Created
- Mar 26, 2026
- Updated
- Mar 27, 2026