Original	Prompt	Result
photo.jpg	“oil painting style”	Painterly version
landscape.jpg	“add dramatic sunset colors”	Enhanced sky

image	prompt	negative_prompt
	oil painting style, vibrant colors, brushstrokes visible	blurry, low quality, bad anatomy
	watercolor painting, soft edges, artistic	blurry, low quality, bad anatomy

image	prompt	image_to_image
	oil painting style, vibrant colors, brushstrokes visible

image	prompt	negative_prompt	image_to_image
	oil painting style, vibrant colors, brushstrokes visible	blurry, low quality, bad anatomy

image	prompt	negative_prompt	transformed
	oil painting style, vibrant colors, brushstrokes visible	blurry, low quality, bad anatomy
	watercolor painting, soft edges, artistic	blurry, low quality, bad anatomy

## Solution **What’s in this recipe:** * Transform images using text prompts with Hugging Face Stable Diffusion models * Control transformation strength and quality settings * Process batches of images automatically You can iterate on transformations before adding them to your table. Use `.select()` with `.collect()` to preview results on sample images—nothing is stored in your table. If you want to collect only the first few rows, use `.head(n)` instead of `.collect()`. Once you’re satisfied, use `.add_computed_column()` to apply the transformation to all images in your table. For more on this workflow, see [Get fast feedback on transformations](/howto/cookbooks/core/dev-iterative-workflow). ### Setup ```python theme={null} %pip install -qU pixeltable torch transformers diffusers accelerate ``` ```python theme={null} import pixeltable as pxt from pixeltable.functions.huggingface import image_to_image ``` ### Load images ```python theme={null} # Create a fresh directory (drop existing if present) pxt.drop_dir('img2img_demo', force=True) pxt.create_dir('img2img_demo') ```

  Connected to Pixeltable database at: postgresql+psycopg://postgres:@/pixeltable?host=/Users/cpestano/.pixeltable/pgdata
  Created directory 'img2img\_demo'.
  \

```python theme={null} t = pxt.create_table( 'img2img_demo/images', { 'image': pxt.Image, 'prompt': pxt.String, 'negative_prompt': pxt.String, }, ) ```

  Created table 'images'.

```python theme={null} t.insert( [ { 'image': 'https://raw.githubusercontent.com/pixeltable/pixeltable/main/docs/resources/images/000000000285.jpg', 'prompt': 'oil painting style, vibrant colors, brushstrokes visible', 'negative_prompt': 'blurry, low quality, bad anatomy', }, { 'image': 'https://raw.githubusercontent.com/pixeltable/pixeltable/main/docs/resources/images/000000000776.jpg', 'prompt': 'watercolor painting, soft edges, artistic', 'negative_prompt': 'blurry, low quality, bad anatomy', }, ] ) ```

  Inserted 2 rows with 0 errors in 0.49 s (4.07 rows/s)
  2 rows inserted.

```python theme={null} # View original images and prompts t.collect() ```

### Iterate: test transformation on a single image Use `.select()` to define the transformation, then `.head(n)` to preview results on a subset of images. Nothing is stored in your table. The `image_to_image` function requires: * `image`: The source image to transform * `prompt`: Text describing the desired output * `model_id`: A Hugging Face model ID that supports image-to-image (e.g., `stable-diffusion-v1-5/stable-diffusion-v1-5`) ```python theme={null} # Preview transformation on first image t.select( t.image, t.prompt, image_to_image( t.image, t.prompt, model_id='stable-diffusion-v1-5/stable-diffusion-v1-5', ), ).head(1) ```

### Iterate: adjust transformation strength You control how much the model modifies the original image using `strength` (0.0-1.0): * **Lower values** (0.3-0.5): Subtle changes, preserves more of the original * **Higher values** (0.7-1.0): Dramatic changes, more creative freedom You pass additional parameters through `model_kwargs`. For example, `negative_prompt` text describing what you don’t want the output to be. ```python theme={null} # Preview with lower strength (more preservation of original) t.select( t.image, t.prompt, t.negative_prompt, image_to_image( t.image, t.prompt, model_id='stable-diffusion-v1-5/stable-diffusion-v1-5', model_kwargs={ 'negative_prompt': t.negative_prompt, 'strength': 0.5, 'num_inference_steps': 30, }, ), ).head(1) ```

### Add: apply transformation to all images Once you’re satisfied with the results, use `.add_computed_column()` with the same expression. This processes all rows and stores the results permanently in your table. ```python theme={null} # Save as computed column t.add_computed_column( transformed=image_to_image( t.image, t.prompt, model_id='stable-diffusion-v1-5/stable-diffusion-v1-5', model_kwargs={ 'strength': 0.5, 'num_inference_steps': 25, 'negative_prompt': t.negative_prompt, }, ) ) ```

  Added 2 column values with 0 errors in 53.83 s (0.04 rows/s)
  2 rows updated.

```python theme={null} # View original and transformed images side by side t.select(t.image, t.prompt, t.negative_prompt, t.transformed).collect() ```

### Use reproducible results with seeds You set a `seed` parameter to get the same output every time you run the transformation. ```python theme={null} # Add reproducible transformation t.add_computed_column( transformed_seeded=image_to_image( t.image, t.prompt, model_id='stable-diffusion-v1-5/stable-diffusion-v1-5', seed=42, model_kwargs={ 'strength': 0.5, 'negative_prompt': t.negative_prompt, }, ) ) ```

  Added 2 column values with 0 errors in 96.24 s (0.02 rows/s)
  2 rows updated.

```python theme={null} # View results t.select(t.image, t.transformed_seeded).collect() ```

## Explanation **How image-to-image works:** Image-to-image diffusion models take an existing image and a text prompt, then generate a new image that blends the structure of the original with the guidance from the prompt. The `strength` parameter controls the balance—lower values preserve more of the original, while higher values allow more dramatic transformations. **Model compatibility:** The `image_to_image` UDF uses `AutoPipelineForImage2Image` from the diffusers library, which automatically detects the model type and selects the appropriate pipeline. You use any compatible model: * `stable-diffusion-v1-5/stable-diffusion-v1-5` - General-purpose, runs on most hardware * `stabilityai/stable-diffusion-xl-base-1.0` - Higher quality, needs more VRAM **Key parameters:** * `strength` (0.0-1.0): How much to transform the image * `negative_prompt`: Text describing what to avoid in the generated image (e.g., “blurry, low quality”). * `num_inference_steps`: Quality vs speed tradeoff (more steps = better quality) * `guidance_scale`: How closely to follow the prompt (7-8 is typical) * `seed`: For reproducible results ## See also * [Apply filters to images](/howto/cookbooks/images/img-apply-filters) * [Generate captions for images](/howto/cookbooks/images/img-generate-captions) * [Hugging Face image-to-image models](https://huggingface.co/models?pipeline_tag=image-to-image) Built with [Mintlify](https://mintlify.com).

image	transformed_seeded