anaksor-ocr
Sokheng · Kit
Reads Khmer and English text from documents, receipts and photos of signs, using a detector for text lines and a recogniser for each line. Suits developers who…
A third-party copy of Krea 2 model files, based on Krea-2-Turbo, with a summary of the Krea 2 Community License. The card does not describe the model's task.
krea-2_model is a kit in the Developer category, listed by Mindket. It is free. This is version 1, last updated on . Download it on this page, a zip of its files. Nothing in it runs by itself.
pip install -U huggingface_hub hf download Kerstal/krea-2_model
This repository by Kerstal holds model files for Krea 2, based on krea/Krea-2-Turbo. The card says the Krea 2 model covers both a Raw and a Turbo variant. It is a re-upload, not the original publisher's page.
The card says nothing about what the model produces or how to run it. Its text is a plain-language summary of the Krea 2 Community License, followed by a disclaimer. Read the original Krea 2 pages for the technical details.
People who already know Krea 2 and want a copy of its weights, and small studios that want to fine-tune or build LoRAs under the community license.
| Industry | Who uses it | How they use it | Example |
|---|---|---|---|
| Creative | Small studios | Use the model within the license revenue cap | A studio under the cap making client work |
| Research | Model researchers | Study and modify the weights | Fine-tuning a variant for an experiment |
| Software | Developers | Build and share LoRAs on top | Publishing a custom LoRA |
You can skip it if you need documentation, a demo or a task description, or if your company earns above the license revenue cap and has no enterprise license.
The card names no runner or app. Check the original Krea 2 pages for supported tools. The download step works on Windows, macOS and Linux with Python.
| Use case | Who | What they get back |
|---|---|---|
| Local copy of the weights | Developers | The files for Krea 2 variants in one repository |
| Custom LoRAs | Creators | Permission to train and share LoRAs, per the card |
| Commercial work under the cap | Small companies | Permission to use outputs commercially below the revenue limit |
You need Python and the Hugging Face tools to fetch the files. The card gives no further setup, so follow the original Krea 2 instructions for running the model.
pip install -U huggingface_hub hf download Kerstal/krea-2_model
The card gives no usage steps. It only states the license terms and a disclaimer, so use the original Krea 2 pages for how to run the model.
A small studio with annual revenue under 1,000,000 USD downloads the files and trains a custom LoRA. The card says this is allowed, including sharing the LoRA, though what the model generates is not stated in the card.
If you are new, the most useful thing to know is the license. Use under the revenue cap, ask for an enterprise license above it, and moderate content if you host the model for others.
If you know the field, the card separates the weights, under the Krea 2 Community License, from the inference code repository, under Apache 2.0. The Hugging Face license tag shows Apache 2.0, so read the card's text rather than the tag alone.
The maintainer says all rights stay with the original creators and asks to be contacted for removal. Downloading means you are solely responsible for how you use the model, and the maintainer takes no liability for outputs.
A third-party copy of Krea 2 model files, based on Krea-2-Turbo, with a summary of the Krea 2 Community License. The card does not describe the model's task.
Made by Kerstal on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face.
What it is: This repository by Kerstal holds model files for Krea 2, based on krea/Krea-2-Turbo. The card says the Krea 2 model covers both a Raw and a Turbo variant. It is a re-upload, not the original publisher's page.
The card says nothing about what the model produces or how to run it. Its text is a plain-language summary of the Krea 2 Community License, followed by a disclaimer. Read the original Krea 2 pages for the technical details.
Who it suits: People who already know Krea 2 and want a copy of its weights, and small studios that want to fine-tune or build LoRAs under the community license.
Industry | Who uses it | How they use it | Example
Creative | Small studios | Use the model within the license revenue cap | A studio under the cap making client work
Research | Model researchers | Study and modify the weights | Fine-tuning a variant for an experiment
Software | Developers | Build and share LoRAs on top | Publishing a custom LoRA
You can skip it if you need documentation, a demo or a task description, or if your company earns above the license revenue cap and has no enterprise license.
Where to use it: The card names no runner or app. Check the original Krea 2 pages for supported tools. The download step works on Windows, macOS and Linux with Python.
Use case | Who | What they get back
Local copy of the weights | Developers | The files for Krea 2 variants in one repository
Custom LoRAs | Creators | Permission to train and share LoRAs, per the card
Commercial work under the cap | Small companies | Permission to use outputs commercially below the revenue limit
How to set it up: You need Python and the Hugging Face tools to fetch the files. The card gives no further setup, so follow the original Krea 2 instructions for running the model.
pip install -U huggingface_hub
hf download Kerstal/krea-2_model
How to use it: The card gives no usage steps. It only states the license terms and a disclaimer, so use the original Krea 2 pages for how to run the model.
Example: A small studio with annual revenue under 1,000,000 USD downloads the files and trains a custom LoRA. The card says this is allowed, including sharing the LoRA, though what the model generates is not stated in the card.
For newcomers and experts: If you are new, the most useful thing to know is the license. Use under the revenue cap, ask for an enterprise license above it, and moderate content if you host the model for others.
If you know the field, the card separates the weights, under the Krea 2 Community License, from the inference code repository, under Apache 2.0. The Hugging Face license tag shows Apache 2.0, so read the card's text rather than the tag alone.
Download the files
Check the community license terms
Run with the original Krea 2 tools
Moderate content if you serve others
Good to know: The maintainer says all rights stay with the original creators and asks to be contacted for removal. Downloading means you are solely responsible for how you use the model, and the maintainer takes no liability for outputs.
Download its files with Hugging Face's command line:
pip install -U huggingface_hub
hf download Kerstal/krea-2_model
Then follow the usage in its model card. Nothing in this kit runs by itself.
README.md 5 KB
Listed Hugging Face models in the same category that share the most tags with this one.
| Product | Downloads, last 30 days | Likes | Parameters | License | Last change |
|---|---|---|---|---|---|
| krea-2_model This page | 0 | 33 | — | apache-2.0 | |
| Krea2 Turbo OpenPose ControlNet LoRAShares krea2 | 18,552 | 133 | — | apache-2.0 | |
| MOSS-Image-SFT-4-stepsShares turbo | 73,131 | 96 | 5.1B | apache-2.0 | |
| Idol Turbo by speridlabsShares turbo | 565 | 57 | — | apache-2.0 |
Sokheng · Kit
Reads Khmer and English text from documents, receipts and photos of signs, using a detector for text lines and a recogniser for each line. Suits developers who…
Qwen · Kit
Qwen2.5-7B-Instruct as GGUF files in eight quantization sizes, to chat with locally through llama.cpp. For people who want a capable 7.6B model on their own co…
ACE-Step · Kit
Generates music from text with a 4B diffusion decoder, 50 steps and guidance control, aiming for higher audio quality than the base. For creators with a GPU of…
alirezarezvani · Skill
Adds 411 ready-made skills for Claude Code and other coding agents, grouped by role from engineering and product to marketing, finance and compliance. Installs…
block · Kit
Self-hostable workspace where people and AI agents share the same rooms, built on a Nostr relay that logs every action as a signed event. For teams that want t…
backnotprop · Kit
Opens your AI coding agent's plans, specs and code changes in a browser so you can annotate or comment on them and send the feedback straight back to the agent.