A 70.8M-parameter text-to-image model for pixel art, flat icons and stickers. Small enough for laptops and, next, the browser. Part of Darkroom, a project to build tiny image generators that run where you are. The same held-out prompts, never seen in training, from the 0.6B teacher and from each Pinhole size: ONNX Runtime Web (WebAssembly or WebGPU), so prompts and images never leave the browser. Parity: the ONNX-only pipeline matches PyTorch to within a mean of 0.00/255 per pixel (same noise, 20 steps). The browser's tokenizer is checked against Python by the demo's Self-test button. Start with one of the three styles, then describe a simple subject: of a. - Adjust guidance with cfg: 3–6…
QWEN_2.1_HDR_VAE is an open-weight model for text to image from User Name, released under other. It has 338M parameters. At 16-bit it needs about 0.8 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
Fine-tuned Qwen Image 2.1 autoencoder for RGBA / HDR-oriented reconstruction. The goal is stronger dynamic range, color volume, and detail energy for HDR-style workflows—not perfect fidelity to the source frame.
Parameters338M
Context—
Weights1.4 GB
Licenseother
AccessOpen weights
Monthly Downloads—
Runs On
What it takes to serve QWEN_2.1_HDR_VAE (338M 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 | 0.7 GB | 0.8 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.3 GB | 0.4 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.2 GB | 0.2 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.
QWEN_2.1_HDR_VAE on every accelerator the SAVRN Index prices, at every precision
Model Card
Fine-tuned Qwen Image 2.1 autoencoder for RGBA / HDR-oriented reconstruction. The goal is stronger dynamic range, color volume, and detail energy for HDR-style workflows—not perfect fidelity to the source frame. Relative to ground truth and compared with base Qwen 2.1 VAE (VAE A): VAE B deliberately overshoots GT on Lab color volume, edge density, and gradient energy. VAE A stays closer to GT on SSIM/PSNR but compresses color volume and softens detail. That tradeoff is the point of this checkpoint. - Uses the VAE’s own latentsmean / latentsstd (no FLUX/SD 0.18215 scaling) - Trained / evaluated around 512–1024 resolution; spatial size should be divisible by 16 - HDR-oriented encode/decode in…
Excerpt from the card by User Name, licensed other.
Identity and Version
- Repository
- Felldude/QWEN_2.1_HDR_VAE
- Publisher
- User Name
- Task
- Text to image
- Modality
- Image
- Library
- diffusers
- Parameters
- 338M parameters
- Languages
- hdr, vae
- Revision
- 0d5915192939f5a62757972bd02006d1b70614e7
- First published
- 2026-09-22
- Last updated
- 2026-09-22
Files and Weights
4 files, 1.4 GB in total. The weights are 1 file totalling 1.4 GB in safetensors.
Weights1 file · 1.4 GB
Configuration1 file · 2.1 KB
Documentation1 file · 2.7 KB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| diffusion_pytorch_model.safetensors | Weights | 1.4 GB | 7c4959edc6f9 |
| config.json | Configuration | 2.1 KB | — |
| README.md | Documentation | 2.7 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- other
- Access
- Open weights, no gate
- Download size
- 1.4 GB
Download from User Name
Released by User Name through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 1.4 GB |
| 16-bit | 0.7 GB |
| 8-bit | 0.3 GB |
| 4-bit | 0.2 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About QWEN_2.1_HDR_VAE
How much GPU memory does QWEN_2.1_HDR_VAE need?
About 0.8 GB at 16-bit and 0.2 GB at 4-bit: the weights (338M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run QWEN_2.1_HDR_VAE 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.
What license is QWEN_2.1_HDR_VAE released under?
other, as its publisher declares it. Read the license text before commercial use.
Similar Models
A 34.4M-parameter text-to-image model for pixel art, flat icons and stickers. Small enough for laptops and, next, the browser. Part of Darkroom, a project to build tiny image generators that run where you are. The same held-out prompts, never seen in training, from the 0.6B teacher and from each Pinhole size: ONNX Runtime Web (WebAssembly or WebGPU), so prompts and images never leave the browser. Parity: the ONNX-only pipeline matches PyTorch to within a mean of 0.00/255 per pixel (same noise, 20 steps). The browser's tokenizer is checked against Python by the demo's Self-test button. Start with one of the three styles, then describe a simple subject: of a. - Adjust guidance with cfg: 3–6…
A 13.1M-parameter text-to-image model for pixel art, flat icons and stickers. Small enough for laptops and, next, the browser. Part of Darkroom, a project to build tiny image generators that run where you are. The same held-out prompts, never seen in training, from the 0.6B teacher and from each Pinhole size: ONNX Runtime Web (WebAssembly or WebGPU), so prompts and images never leave the browser. Parity: the ONNX-only pipeline matches PyTorch to within a mean of 0.00/255 per pixel (same noise, 20 steps). The browser's tokenizer is checked against Python by the demo's Self-test button. Start with one of the three styles, then describe a simple subject: of a. - Adjust guidance with cfg: 3–6…
This is a modular diffusion pipeline built with Diffusers' modular pipeline framework. Description: Auto Modular pipeline for text-to-image and image-conditioned generation using Qwen-Image 2.1. - for text-to-image generation, all you need to provide is prompt - for image-conditioned generation, you need to provide prompt and image (one image or a list) This pipeline uses a 4-block architecture that can be customized and extended. [TODO] This modular pipeline is composed of the following blocks: 1. textencoder (QwenImage21AutoTextEncoderStep) - Text encoder step that encodes the prompt, together with the condition images when there are any. 2. vaeencoder (QwenImage21AutoVaeEncoderStep)…
GGUF, Safetensors, and MLX quantized formats of Qwen/Qwen-Image-2.1 for local image generation using the original upstream base weights. Q4KM is recommended for the best balance of size and quality for GGUF. INT8 ConvRot and NVFP4 offer high performance on supported GPUs, while MLX formats are optimized for Apple Silicon. Companion model files packaged for ComfyUI: Use the model with ComfyUI and ComfyUI-GGUF. All required companion files (GGUF transformer, text encoder, and VAE) are hosted directly in this repository. Download the files and place them in their respective ComfyUI directories: 1. Install ComfyUI-GGUF: Use the maintained fork with native Qwen-Image 2.1 support by cloning…
GGUF quantizations of Qwen/Qwen-Image-2.1 for local image generation using the original upstream base weights. Q4KM is recommended for the best balance of size and quality. Companion model files packaged for ComfyUI: Use the model with ComfyUI and ComfyUI-GGUF. All required companion files (GGUF transformer, text encoder, and VAE) are hosted directly in this repository. Download the files and place them in their respective ComfyUI directories: 1. Install ComfyUI-GGUF: Use the maintained fork with native Qwen-Image 2.1 support by cloning leejet/ComfyUI-GGUF into your custom nodes: (Note: If you have the older city96/ComfyUI-GGUF installed and encounter an Unknown model architecture! error…