| | --- |
| | tags: |
| | - text-to-image |
| | - lora |
| | - diffusers |
| | - template:diffusion-lora |
| | widget: |
| | - output: |
| | url: images/pixel_composite.png |
| | text: Make the sea shell red |
| | - output: |
| | url: images/pixel_composite.png |
| | text: '-' |
| | base_model: FreedomIntelligence/Janus-4o-7B |
| | instance_prompt: null |
| | license: mit |
| | datasets: |
| | - osunlp/MagicBrush |
| | --- |
| | # ThinkClearly |
| |
|
| | https://github.com/peterN908/ThinkClearly/tree/main |
| |
|
| |
|
| | ## Model description |
| |
|
| | A conceptual exploration of tool use in AR image models |
| |
|
| | We fine-tune Janus 4o models to produce `<CLEAR>` instruction tokens when making text+image to image edits. This indicate that this token patch should be an exact pixel match to the input image |
| |
|
| |
|
| |
|
| | ## Download model |
| |
|
| |
|
| | [Download](/peterface/ThinkClearly/tree/main) them in the Files & versions tab. |
