--- pipeline_tag: image-to-image tags: - image-to-image - lora - diffusers - template:diffusion-lora widget: - output: url: images/example_001.png text: transform into anime - output: url: images/example_002.png text: transform into anime - output: url: images/example_003.png text: transform into anime - output: url: images/example_004.png text: transform into anime - output: url: images/example_005.png text: transform into anime license: apache-2.0 --- # Photo To Anime Lora ## Model description This is an image-editing LoRA. Provide an input image and an instruction describing the edit. **Trigger word:** use `transform into anime` in your instructions for best results. The examples below show input → output for different instructions. ## Trigger word Include **`transform into anime`** in your edit instruction, for example: ``` transform into anime ``` ## Gallery ### Example 1 ![Example 1](images/example_001.png) *Prompt:* transform into anime *Input:* ![Input 1](images/input_001.png) ### Example 2 ![Example 2](images/example_002.png) *Prompt:* transform into anime *Input:* ![Input 2](images/input_002.png) ### Example 3 ![Example 3](images/example_003.png) *Prompt:* transform into anime *Input:* ![Input 3](images/input_003.png) ### Example 4 ![Example 4](images/example_004.png) *Prompt:* transform into anime *Input:* ![Input 4](images/input_004.png) ### Example 5 ![Example 5](images/example_005.png) *Prompt:* transform into anime *Input:* ![Input 5](images/input_005.png) ## LoRA scale The gallery was generated with **`lora_scale=1.0`**. You can tune this when running inference (e.g. lower for a subtler effect, higher for a stronger style). ## Use on Replicate ```python import replicate output = replicate.run( "prunaai/p-image-edit-lora:17651bd22e8c151cdb13a97b0f8554dce1e7238cd0a18cf90bc237ac5f0bc067", input={ "images": ["https://example.com/input.png"], "prompt": "transform into anime your edit instruction", "lora_weights": "https://huggingface.co/davidberenstein1957/p-image-edit-photo-to-anime-lora/resolve/main/weights.safetensors", "lora_scale": 1.0, "hf_api_token": "your-hf-token", } ) ```