## Basic model info

Model name: prunaai/hidream-e1.1
Model description: Edit an image with a prompt. This is the hidream-e1.1 model accelerated with the pruna optimisation engine.


## Model inputs

- prompt (required): Prompt (string)
- speed_mode (optional): Speed optimization level (string)
- image (optional): Input image to edit. (string)
- seed (optional): Random seed (-1 for random) (integer)
- output_format (optional): Output format (string)
- output_quality (optional): Output quality (for jpg and webp) (integer)
- guidance_scale (optional): Guidance scale (number)
- num_inference_steps (optional): Number of inference steps (integer)
- image_guidance_scale (optional): Image guidance scale (number)
- refine_strength (optional): Strength of refinement (number)
- clip_cfg_norm (optional): Whether to use CLIP CFG normalization (boolean)


## Model output schema

{
  "type": "string",
  "title": "Output",
  "format": "uri"
}

If the input or output schema includes a format of URI, it is referring to a file.


## Example inputs and outputs

Use these example outputs to better understand the types of inputs the model accepts, and the types of outputs the model returns:

### Example (https://replicate.com/p/bbjhd2x6fnrm80cr8wtbvcza1w)

#### Input

```json
{
  "seed": -1,
  "image": "https://raw.githubusercontent.com/HiDream-ai/HiDream-E1/refs/heads/main/assets/test_1.png",
  "prompt": "Convert the image into a 3D animated style.",
  "speed_mode": "Extra Juiced \ud83d\ude80 (even more speed)",
  "clip_cfg_norm": true,
  "output_format": "webp",
  "guidance_scale": 3.5,
  "output_quality": 80,
  "refine_strength": 0.3,
  "num_inference_steps": 28,
  "image_guidance_scale": 2
}
```

#### Output

```json
"https://replicate.delivery/xezq/D8DZOH9C8LY3Op58qCrhN8205eRKNSCqopGb9xBeyKK4ypEVA/output_513307_0.webp"
```


## Model readme

> No readme available for this model.