This model is a diffusion model for unconditional image generation of cute.
Open-weight model · Unconditional image generation
ddpm-celebahq-finetuned-butterflies-2epochs
by Sen Zheng SenZh/ddpm-celebahq-finetuned-butterflies-2epochs
ddpm-celebahq-finetuned-butterflies-2epochs is an open-weight model for unconditional image generation from Sen Zheng, released under MIT License. It has 114M parameters. At 16-bit it needs about 0.3 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
Describe your model here
Parameters114M
Context—
Weights454.7 MB
Licensemit
AccessOpen weights
Monthly Downloads—
Runs On
What it takes to serve ddpm-celebahq-finetuned-butterflies-2epochs (114M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 0.2 GB | 0.3 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.1 GB | 0.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.1 GB | 0.1 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 Oct 18, 2026.
Model Card
By Sen Zheng, published under mit, revision f80f4f46603c.
Describe your model here
Read Sen Zheng's full model card
Example Fine-Tuned Model for Unit 2 of the Diffusion Models Class
Describe your model here
Usage
from diffusers import DDPMPipeline
pipeline = DDPMPipeline.from_pretrained('SenZh/ddpm-celebahq-finetuned-butterflies-2epochs')
image = pipeline().images[0]
image
Identity and Version
- Repository
- SenZh/ddpm-celebahq-finetuned-butterflies-2epochs
- Publisher
- Sen Zheng
- Task
- Unconditional image generation
- Modality
- Other
- Library
- diffusers
- Parameters
- 114M parameters
- Languages
- Not stated by the source
- Revision
- f80f4f46603cea2527a4cdcfe48b8dbf1fd74c23
- First published
- 2026-10-03
- Last updated
- 2026-10-03
Files and Weights
6 files, 454.7 MB in total. The weights are 1 file totalling 454.7 MB in safetensors.
Weights1 file · 454.7 MB
Configuration3 files · 2.0 KB
Documentation1 file · 453 B
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| diffusion_pytorch_model.safetensors | Weights | 454.7 MB | 06386c7b5eb0 |
| config.json | Configuration | 1.3 KB | — |
| model_index.json | Configuration | 228 B | — |
| scheduler_config.json | Configuration | 525 B | — |
| README.md | Documentation | 453 B | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- mit
- Access
- Open weights, no gate
- Download size
- 454.7 MB
Download from Sen Zheng
Released by Sen Zheng through its official repository on Hugging Face. Read the license.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 454.7 MB |
| 16-bit | 0.2 GB |
| 8-bit | 0.1 GB |
| 4-bit | 0.1 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About ddpm-celebahq-finetuned-butterflies-2epochs
How much GPU memory does ddpm-celebahq-finetuned-butterflies-2epochs need?
About 0.3 GB at 16-bit and 0.1 GB at 4-bit: the weights (114M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run ddpm-celebahq-finetuned-butterflies-2epochs 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 ddpm-celebahq-finetuned-butterflies-2epochs commercially?
Yes. ddpm-celebahq-finetuned-butterflies-2epochs 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.
Similar Models
Official checkpoints for FuseReg. FuseReg replaces heuristic encoder-layer fusion in representation autoencoders (RAEs) with training over random subsets of encoder layers, so a single pixel decoder reconstructs reliably under any layer-subset fusion and pairs better with the diffusion generator. The repository currently contains 16 inference checkpoints: eight DINOv3-L k=23 decoders, two DINOv3-L k=7 decoders, and six DiT-XL generators. The k=7 p=0.3, four EUPE, and four SigLIP variants have not been published. A 25-file candidate collection is tracked in the checkpoint manifest; only entries in its files array are available for download. Checkpoint manifest records file size, SHA-256…