Surjo-Image-Preview-ONNX by Mrfakename: Open-Weight Model

Model Card

By Mrfakename, published under apache-2.0, revision 831f3d972d1c.

ONNX export of SurjoLabs/Surjo-Image-Preview for the browser (onnxruntime-web, WebGPU), together with its text encoder LiquidAI/LFM2.5-Encoder-230M and VAE decoder fp16w means weights are stored in fp16 and computed in fp32 (image PSNR about 60 dB against PyTorch fp32). An int4 text encoder was tried and dropped: it changed the pictures too much. Sampling: start from standard normal noise, t = i/steps, dt = 1/steps, 50 steps, cfg 3.0. onnx/parity.json has the image PSNR against the PyTorch fp32 pipeline.

Read Mrfakename's full model card

ONNX export of SurjoLabs/Surjo-Image-Preview for the browser (onnxruntime-web, WebGPU), together with its text encoder LiquidAI/LFM2.5-Encoder-230M and VAE decoder SurjoLabs/FLUX.2-small-decoder-vae.

file	what
`onnx/text_encoder_*.onnx`	`input_ids`, `attention_mask` (1,128) int64 -> `hidden` (1,128,1024). Pad to 128 on the right with `<\|pad\|>`.
`onnx/dit_step_*.onnx`	one classifier-free-guided Euler step: `z` (N,128,16,16), `t`, `dt`, `cfg` (1,), `ctx` (2,128,1024) = [empty prompt, prompt], `mask` (2,128) -> `z_next`
`onnx/vae_decoder_*.onnx`	`z` (N,128,16,16) -> `image` (N,3,256,256) in [0,1]; BatchNorm de-normalisation and 2x2 unpatchify are inside

_fp16w means weights are stored in fp16 and computed in fp32 (image PSNR about 60 dB against PyTorch fp32). An int4 text encoder was tried and dropped: it changed the pictures too much. Sampling: start from standard normal noise, t = i/steps, dt = 1/steps, 50 steps, cfg 3.0. onnx/parity.json has the image PSNR against the PyTorch fp32 pipeline.

Identity and Version

Repository: mrfakename/Surjo-Image-Preview-ONNX
Publisher: Mrfakename
Task: Text to image
Modality: Image
Library: onnxruntime
Parameters: Not stated by the source
Languages: Not stated by the source
Revision: 831f3d972d1c16d3a0ca897f1ba16821458db614
First published: 2026-10-15
Last updated: 2026-10-15

Files and Weights

16 files, 739.1 MB in total. The weights are 3 files totalling 733.7 MB in onnx.

Weights3 files · 733.7 MB

Configuration3 files · 6.7 KB

Tokenizer2 files · 4.8 MB

Documentation1 file · 1.4 KB

Other6 files · 606.0 KB

Repository1 file · 1.9 KB

Every file

File	Type	Size	SHA-256
onnx/dit_step_fp16w.onnx	Weights	218.0 MB	781cb6752dfc
onnx/text_encoder_fp16w.onnx	Weights	459.7 MB	1ce1d1008ba1
onnx/vae_decoder_fp16w.onnx	Weights	56.0 MB	fabe57924c07
onnx/meta.json	Configuration	5.3 KB	—
onnx/parity.json	Configuration	1.3 KB	—
special_tokens_map.json	Configuration	120 B	—
README.md	Documentation	1.4 KB	—
samples/fp16w_0.png	Other	98.7 KB	—
samples/fp16w_1.png	Other	103.4 KB	2326a1e5db30
samples/fp32_0.png	Other	98.7 KB	—
samples/fp32_1.png	Other	103.3 KB	d2ffe12df384
samples/torch_0.png	Other	98.7 KB	—
samples/torch_1.png	Other	103.3 KB	c2dd47f4f9a2
.gitattributes	Repository	1.9 KB	—
tokenizer.json	Tokenizer	4.7 MB	—
tokenizer_config.json	Tokenizer	92.0 KB	—

License and Download

License: apache-2.0
Access: Open weights, no gate
Download size: 733.7 MB

Download from Mrfakename

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

Built From

Derived from SurjoLabs/Surjo-Image-Preview
Quantized from SurjoLabs/Surjo-Image-Preview

Memory Requirements

Precision	Weights in memory
As published	733.7 MB

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

Questions About Surjo-Image-Preview-ONNX

Can I use Surjo-Image-Preview-ONNX commercially?

Yes. Surjo-Image-Preview-ONNX is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.

Similar Models

Model · Text to image

Qwen-Image-2.1-Uncensored-Quantized

Ahmet Benzer

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…

Open weights other gguf

View model

Model · Text to image

Qwen-Image-2.1-Uncensored-GGUF

Ahmet Benzer

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…

Open weights other gguf

View model

Model · Text to image

Qwen-Image-2.1-GGUF

Unsloth AI

This is a GGUF quantized version of Qwen-Image-2.1. unsloth/Qwen-Image-2.1-GGUF uses Unsloth Dynamic 2.0 methodology for SOTA performance. - Important layers are upcasted to higher precision, per tensor, from a measured sensitivity scan. - Run these with Unsloth Desktop, stable-diffusion.cpp and more. A GGUF is the denoiser only, so it needs the VAE and the Qwen3-VL text encoder alongside it. See below for image editing operating inside of Unsloth Desktop: Rendered with the Q4KM denoiser and the Q4KM text encoder, 1024x1024, 20 steps, cfg 6.0, euler. We are excited to open-source Qwen-Image-2.1, a unified text-to-image generation and image editing model in the Qwen family. With just 7B…

Open weights other

View model

Model · Text to image

Z-Image-Turbo-GGUF

Unsloth AI

Welcome to the official repository for the Z-Image（造相）project! Z-Image is a powerful and highly efficient image generation model with 6B parameters. Currently there are three variants: - Z-Image-Turbo – A distilled version of Z-Image that matches or exceeds leading competitors with only 8 NFEs (Number of Function Evaluations). It offers sub-second inference latency on enterprise-grade H800 GPUs and fits comfortably within 16G VRAM consumer devices. It excels in photorealistic image generation, bilingual text rendering (English & Chinese), and robust instruction adherence. - Z-Image-Base – The non-distilled foundation model. By releasing this checkpoint, we aim to unlock the full potential…

Open weights apache-2.0 ggml

View model

Model · Text to image

Juggernaut-XL-v9

RunDiffusion

The SDXL ecosystem is the single most mature corner of open image generation, and v9 is its most refined photorealism checkpoint. Choose Juggernaut XL v9 when you want: - Photorealism that holds up under scrutiny — skin texture, micro-contrast, and natural lighting that translates from concept to print. - Reasonable hardware — runs comfortably on 8 GB of VRAM, unlike newer DiT-based models that demand 16+ GB. - The full SDXL toolbox — drop-in compatibility with the thousands of SDXL ControlNets, IP-Adapter variants, AnimateDiff, regional prompting tools, and LoRAs already in your workflow. - Battle-tested reliability — 26+ months in production, used in agencies, studios, and shipping…

Open weights creativeml-openrail-m diffusers

View model

Model · Text to image

Qwen-Image-Lightning

Lightx2v

Please refer to Qwen-Image-Lightning github to learn how to use the models. make sure to install diffusers from main (pip install git+https://github.com/huggingface/diffusers.git)

Open weights apache-2.0 diffusers

View model