ComfyUI Image to Image: Denoise Settings & Common Mistakes

What is Image to Image?

Image to Image (img2img) takes an existing image as input and generates a new image based on it. Instead of starting from pure noise like text-to-image, the model starts from a noisy version of your reference image — preserving its structure while applying new styles or details.

Common use cases:

• Style transfer — turn a photo into anime, oil painting, or sketch
• Photo restoration — clean up old or damaged images
• Colorization — add color to black-and-white photos
• Concept iteration — refine a rough sketch into a polished image

How It Differs from Text to Image

The workflow is almost identical to text-to-image, with two key changes:

1. Input image replaces empty latent — Instead of an Empty Latent Image node, you use a Load Image node followed by a VAE Encode node to convert your reference into latent space
2. Denoise must be less than 1.0 — This is the critical difference

The Denoise Parameter

The denoise value in the KSampler controls how much of the original image the model retains:

Building the Workflow

Step 1: Load Your Reference Image

Add a Load Image node and select your input image. This replaces the Empty Latent Image node from the text-to-image workflow.

Step 2: Encode to Latent Space

Connect the Load Image output to a VAE Encode node. This converts your pixel image into the latent representation that the KSampler works with.

Step 3: Configure the KSampler

Connect everything as you would in a text-to-image workflow, but:

• Set denoise to a value between 0.3 and 0.7 as a starting point
• Write prompts that describe your desired output style
• The model will use your reference as the starting point instead of pure noise

Connection Checklist

Make sure these connections are in place before generating:

• Load Image → VAE Encode (samples input)
• Load Checkpoint → VAE Encode (vae input) and VAE Decode (vae input)
• VAE Encode → KSampler (latent_image input)
• CLIP Text Encode (positive) → KSampler
• CLIP Text Encode (negative) → KSampler
• KSampler → VAE Decode → Save Image

A good starting configuration: steps 20, cfg 7.0, denoise 0.5.

Step 4: Generate and Iterate

Click Queue (or Ctrl+Enter) to generate. If the result is:

• Too close to the original — increase denoise
• Too different from the original — decrease denoise
• Wrong style — adjust your text prompts

Practical Tips

• Start with denoise 0.5 and adjust from there — it's a good middle ground
• Your prompt still matters — it guides what the model adds during denoising
• Negative prompts help — use them to avoid artifacts just like in text-to-image
• Resolution matters — for SD1.5, resize your input to 512×512 for best results
• Experiment systematically — try denoise values from 0.2 to 0.8 in 0.1 increments to find your sweet spot

Common Issues and Fixes

Output looks nothing like my reference

• Denoise too high — lower it to 0.3–0.5 to retain more of the original
• Wrong VAE connection — make sure Load Checkpoint's VAE connects to both VAE Encode and VAE Decode
• Mismatched resolution — resize your input to match the model's native resolution (512×512 for SD1.5)

Output is almost identical to the input

• Denoise too low — increase to 0.5–0.7 for more transformation
• Weak prompt — add more descriptive keywords for the desired style change

Colors or contrast look wrong

• This often happens when the VAE from your checkpoint doesn't match. Try using an external VAE (add a "Load VAE" node) such as vae-ft-mse-840000-ema-pruned

Reference image appears distorted

• Check that your input image dimensions are divisible by 8 (ComfyUI latent space requirement)
• Avoid very small images (<256px) — they don't have enough detail for the model to work with

Next Steps

• Text to Image — If you haven't already, learn the fundamentals
• LoRA Guide — Combine img2img with LoRA for precise style control
• Upscale Guide — Enhance your img2img results with AI upscaling

Source References

• ComfyUI Image to Image tutorial
• ComfyUI Text to Image tutorial
• ComfyUI workflow concept