SAVRN
Search Contact SAVRN

Open-weight model · Unconditional image generation

sd-class-butterflies-32

by Changpan Ye eason1021/sd-class-butterflies-32

This model is a diffusion model for unconditional image generation of cute.

Parameters19M
Context
Weights74.2 MB
Licensemit
AccessOpen weights
Monthly Downloads23

Runs On

What it takes to serve sd-class-butterflies-32 (19M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

PrecisionWeightsMemory neededCheapest setupPer hourAlso fits
16-bit 0.0 GB 0.0 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00
8-bit 0.0 GB 0.0 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00
4-bit 0.0 GB 0.0 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00

Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 18, 2026.

Model Card

By Changpan Ye, published under mit, revision 4962f1ec171c.

This model is a diffusion model for unconditional image generation of cute.

Read Changpan Ye's full model card

Model Card for Unit 1 of the Diffusion Models Class

This model is a diffusion model for unconditional image generation of cute.

Usage

from diffusers import DDPMPipeline

pipeline = DDPMPipeline.from_pretrained('eason1021/sd-class-butterflies-32')
image = pipeline().images[0]
image

Identity and Version

Repository
eason1021/sd-class-butterflies-32
Publisher
Changpan Ye
Task
Unconditional image generation
Modality
Other
Library
diffusers
Parameters
19M parameters
Languages
Not stated by the source
Revision
4962f1ec171cfe12c78fc2dcb6fefc8dc8026f90
First published
2026-09-16
Last updated
2026-09-18

Files and Weights

6 files, 74.2 MB in total. The weights are 1 file totalling 74.2 MB in safetensors.

Weights1 file · 74.2 MB
Configuration3 files · 1.7 KB
Documentation1 file · 479 B
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
diffusion_pytorch_model.safetensorsWeights74.2 MB 3009a11b522d
config.jsonConfiguration1.0 KB
model_index.jsonConfiguration181 B
scheduler_config.jsonConfiguration508 B
README.mdDocumentation479 B
.gitattributesRepository1.5 KB

License and Download

License
mit
Access
Open weights, no gate
Download size
74.2 MB
Download from Changpan Ye

Released by Changpan Ye through its official repository on Hugging Face. Read the license.

Memory Requirements

PrecisionWeights in memory
As published74.2 MB
16-bit0.0 GB
8-bit0.0 GB
4-bit0.0 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About sd-class-butterflies-32

How much GPU memory does sd-class-butterflies-32 need?

About 0 GB at 16-bit and 0 GB at 4-bit: the weights (19M parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run sd-class-butterflies-32 on?

At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.

Can I use sd-class-butterflies-32 commercially?

Yes. sd-class-butterflies-32 is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.