Skip to page content
SAVRN
Search Plan a project

Open-weight model · Text to image

cdn3-hf

by Avik Banerjee theavikb/cdn3-hf

cdn3-hf is an open-weight model for text to image from Avik Banerjee, released under Apache License 2.0. Its published files total 970.6 MB.

A DreamBooth-LoRA for Krea 2, trained on Krea 2 RAW and shown on Krea 2 Turbo. The samples below were generated with this LoRA on Turbo (8 steps). Use the token cdn3 woman to invoke the concept.

Parameters—
Context—
Weights966.4 MB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads—

Model Card

By Avik Banerjee, published under apache-2.0, revision da9df85a2f45.

A DreamBooth-LoRA for Krea 2, trained on Krea 2 RAW and shown on Krea 2 Turbo. The samples below were generated with this LoRA on Turbo (8 steps). Use the token cdn3 woman to invoke the concept.

Read Avik Banerjee's full model card

Krea 2 LoRA — theavikb/cdn3-hf

A DreamBooth-LoRA for Krea 2, trained on Krea 2 RAW and shown on Krea 2 Turbo. The samples below were generated with this LoRA on Turbo (8 steps).

Trigger

Use the token cdn3 woman to invoke the concept.

Samples

"A cdn3 woman in a sleek silver spacesuit standing on the crystalline surface of a neon-lit alien planet under two moons."

"A cdn3 woman wearing a flowing linen dress walking through a sun-drenched Tuscan vineyard during the golden hour."

"A cdn3 woman as a cyberpunk hacker surrounded by holographic screens and glowing blue circuitry in a rainy underground bunker."

Use it with diffusers

import torch
from diffusers import Krea2Pipeline

pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("theavikb/cdn3-hf")
image = pipe("A cdn3 woman in a sleek silver spacesuit standing on the crystalline surface of a neon-lit alien planet under two moons.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")

Identity and Version

Repository
theavikb/cdn3-hf
Publisher
Avik Banerjee
Task
Text to image
Modality
Image
Library
diffusers
Parameters
Not stated by the source
Languages
Not stated by the source
Revision
da9df85a2f455877dbbb9feeef483c768aee7e12
First published
2026-09-26
Last updated
2026-09-26

Files and Weights

14 files, 970.6 MB in total. The weights are 7 files totalling 966.4 MB in bin, safetensors.

Weights7 files · 966.4 MB
Documentation1 file · 1.8 KB
Other5 files · 4.2 MB
Repository1 file · 1.7 KB
Every file
FileTypeSizeSHA-256
checkpoint-1000/optimizer.binWeights195.4 MB 4de02070edc7
checkpoint-1000/pytorch_lora_weights.safetensorsWeights191.9 MB f0b4f30011b3
checkpoint-1000/scheduler.binWeights1.4 KB 95d5da819533
checkpoint-500/optimizer.binWeights195.4 MB f579c1688b36
checkpoint-500/pytorch_lora_weights.safetensorsWeights191.9 MB 7e28f3f56bb4
checkpoint-500/scheduler.binWeights1.4 KB f6b09a32f9bd
pytorch_lora_weights.safetensorsWeights191.9 MB 568858b66bf2
README.mdDocumentation1.8 KB —
checkpoint-1000/random_states_0.pklOther14.8 KB dbbf608cc17e
checkpoint-500/random_states_0.pklOther14.8 KB 32090a5971c2
sample_0.pngOther1.2 MB 9a325fcad194
sample_1.pngOther1.5 MB 311b221b8b82
sample_2.pngOther1.4 MB 46f5183e2d48
.gitattributesRepository1.7 KB —

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
966.4 MB
Download from Avik Banerjee

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

Built From

Memory Requirements

PrecisionWeights in memory
As published966.4 MB

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

Questions About cdn3-hf

Can I use cdn3-hf commercially?

Yes. cdn3-hf 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

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

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