Chitra-Tiny-ONNX by Mrfakename: Open-Weight Model

Model Card

By Mrfakename, published under apache-2.0, revision 863b251b80b7.

ONNX export of udgamlabs/Chitra-Tiny, a 212M-parameter text-to-image model (256×256), for onnxruntime-web on WebGPU. Used by the mrfakename/chitra-tiny-webgpu Space. Weights are stored in fp16 and cast to fp32 inside each graph: half the download, fp32 math. The DiT can't run in fp16 because its residual stream goes far past the fp16 range. Sampling (same as chitratiny.py): tokenize with padding to 77, encode the prompt and the negative prompt (empty by default), start from Gaussian noise, then Euler steps over t = linspace(1, 0, steps+1) with x += (t[i+1] - t[i]) (vuncond + g (vcond - vuncond)), then decode. Defaults: 50 steps, guidance 7. tools/exportonnx.py reproduces the files…

Read Mrfakename's full model card

Chitra Tiny (ONNX, for the browser)

ONNX export of udgamlabs/Chitra-Tiny, a 212M-parameter text-to-image model (256×256), for onnxruntime-web on WebGPU. Used by the mrfakename/chitra-tiny-webgpu Space.

File	What	Inputs → outputs
`onnx/text_encoder.onnx`	google/flan-t5-base encoder (from Xenova/flan-t5-base)	`input_ids`, `attention_mask` int64 [B,77] → `last_hidden_state` [B,77,768]
`onnx/transformer.onnx`	Chitra Tiny DiT	`x` [B,4,32,32], `t` [B], `txt` [B,77,768], `txt_mask` bool [B,77] → `v` [B,4,32,32]
`onnx/vae_decoder.onnx`	stabilityai/sd-vae-ft-mse decoder, includes the 1/0.18215 scaling	`latent` [B,4,32,32] → `image` [B,3,256,256] in [-1,1]

Weights are stored in fp16 and cast to fp32 inside each graph: half the download, fp32 math. The DiT can't run in fp16 because its residual stream goes far past the fp16 range.

Sampling (same as chitra_tiny.py): tokenize with padding to 77, encode the prompt and the negative prompt (empty by default), start from Gaussian noise, then Euler steps over t = linspace(1, 0, steps+1) with x += (t[i+1] - t[i]) * (v_uncond + g * (v_cond - v_uncond)), then decode. Defaults: 50 steps, guidance 7.

tools/export_onnx.py reproduces the files; parity.json has the ONNX-vs-PyTorch check. Apache-2.0 (Chitra Tiny, flan-t5-base) and MIT (sd-vae-ft-mse).

Identity and Version

Repository: mrfakename/Chitra-Tiny-ONNX
Publisher: Mrfakename
Task: Text to image
Modality: Image
Library: onnx
Parameters: Not stated by the source
Languages: Not stated by the source
Revision: 863b251b80b7ed8f40b2396e23074c129cdf351a
First published: 2026-10-15
Last updated: 2026-10-15

Files and Weights

11 files, 746.2 MB in total. The weights are 3 files totalling 743.8 MB in onnx.

Weights3 files · 743.8 MB

Configuration4 files · 6.8 KB

Tokenizer2 files · 2.4 MB

Documentation1 file · 1.8 KB

Repository1 file · 1.5 KB

Every file

File	Type	Size	SHA-256
onnx/text_encoder.onnx	Weights	219.5 MB	5cfe25050cc2
onnx/transformer.onnx	Weights	425.1 MB	cad5d2974b32
onnx/vae_decoder.onnx	Weights	99.2 MB	c5c77e970218
chitra_config.json	Configuration	609 B	—
parity.json	Configuration	460 B	—
special_tokens_map.json	Configuration	2.2 KB	—
tools/export_onnx.py	Configuration	3.6 KB	—
README.md	Documentation	1.8 KB	—
.gitattributes	Repository	1.5 KB	—
tokenizer.json	Tokenizer	2.4 MB	—
tokenizer_config.json	Tokenizer	2.3 KB	—

License and Download

License: apache-2.0
Access: Open weights, no gate
Download size: 743.8 MB

Download from Mrfakename

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

Built From

Derived from udgamlabs/Chitra-Tiny
Quantized from udgamlabs/Chitra-Tiny

Memory Requirements

Precision	Weights in memory
As published	743.8 MB

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

Questions About Chitra-Tiny-ONNX

Can I use Chitra-Tiny-ONNX commercially?

Yes. Chitra-Tiny-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