Transform a source image with img2img in Forge

Open Img2img, then choose the img2img sub-tab. Upload a source image or use the gallery button that sends the selected image and its generation parameters to img2img.

It encodes a source image, adds a seed-dependent noise path according to denoising strength, and samples a new result under the prompt and model conditioning. Ordinary img2img applies this transformation to the whole frame.

Txt2img starts without source pixels. Img2img starts from an encoded source image, so its composition, colors and shapes can influence the result depending on denoising and geometry.

Ordinary img2img transforms the whole source. Inpainting adds a mask so a region or its inverse becomes the edit contract. Use the separate inpainting guide for local repair, removal or replacement.

Both. The source supplies initial spatial and visual evidence; the prompt supplies the requested interpretation. Denoising strength controls how much sampling freedom exists to move away from the encoded source.

It selects how much of the img2img noise and sampling schedule is used. Lower values usually preserve more source structure; higher values permit larger change, but the relationship is not a literal similarity percentage.

The current code accepts 0, but the sampling path has effectively no denoising segment. Treat it as a diagnostic boundary for the encoded/resized source—not a useful transformation setting or a guarantee of pixel-identical output.

The UI accepts 1, while sampling code caps its schedule calculation just below 1. This gives very high departure from the source; composition or identity can disappear.

There is no universal value. Compare separated probes with the same source, prompt, seed, model, sampler and dimensions, then narrow the interval that completes the task with the least unnecessary drift.

The prompt may not request a visible change, denoising may be too low for that task, or the fixed source signal may dominate. Raise only denoising first and compare against the same receipt.

Lower denoising and restore a fixed seed. Confirm that target dimensions, resize mode, prompt, model and extensions did not also change when the image was sent or uploaded.

Only when the source and the rest of the effective setup also match: model files, prompt, dimensions, resize mode, sampler, scheduler, steps, denoising, CFG, precision and enabled add-ons.

It changes the noise path applied to the encoded source. A different seed can produce another valid interpretation at the same denoising strength, so keep it fixed while diagnosing denoising.

Use lower denoising, matching geometry and a prompt that does not contradict identity. Ordinary img2img cannot guarantee identity; use inpainting for a protected local region or a separately verified identity tool when exact likeness is required.

Match the source aspect ratio, start with lower denoising and keep the seed fixed. If pose or edges must be explicit constraints rather than tendencies, add one proven ControlNet unit after the base img2img pass works.

Keep the source composition, replace contradictory style terms in the prompt and compare low-to-middle denoising probes. Verify that the target treatment is consistent across the whole frame.

Name the new subject, remove the old one from the prompt and compare wider denoising probes. Expect a transition interval where old and new visual traits mix before replacement becomes clear.

Match the source ratio whenever possible. Otherwise use Just resize only when distortion is acceptable, Crop and resize when losing centered overflow is acceptable, or Resize and fill when preserving the full source is more important than clean new bands.

It resizes the source directly to the target width and height. If source and target aspect ratios differ, shapes are stretched or compressed before diffusion.

It preserves aspect ratio, enlarges the source until the target is filled, centers it, and crops the overflow. Edge content may be removed.

It preserves aspect ratio, fits the source inside the target, and fills empty bands from stretched edge data before diffusion processes the image. It is not the same as intentional outpainting.

Forge skips the ordinary pixel resize, encodes the source, then bilinearly interpolates the latent to the target dimensions. It does not expose a choice of ESRGAN-style upscaler in that mode.

Resize to sets an explicit target width and height. Resize by derives the target from the source dimensions and a 0.05–4.00 scale value; the single-image path rounds dimensions down to multiples of 8.

Use the Auto detect size from img2img button. Automatic width and height updates on image load are controlled by a separate setting that is off in the inspected defaults.

It can output larger dimensions and may run the configured img2img pixel upscaler during ordinary resize, but diffusion still regenerates the image. Use the upcoming upscale guide or Extras when enlargement—not reinterpretation—is the dominant task.

Yes. The Batch sub-tab accepts uploaded files or a server directory when directory access is allowed. Prove one image first, then record batch count, batch size, source handling and output naming.

For selected properties, Forge reads PNG information and appends source Prompt and Negative prompt to the UI prompts; it can also take Seed, CFG scale, Sampler, Steps and Model hash. Audit the resulting prompt before a large run.

A dated video demonstrates one FLUX Dev NF4 setup. That proves one historical combination, not arbitrary current FLUX, GGUF, NF4, LoRA or extension compatibility. Record the complete model package and treat untested combinations as UNKNOWN.

No special img2img filename is required for the core route, but the checkpoint, VAE, text encoders, preset and add-ons must form a compatible model package. Follow the model publisher for family-specific requirements.

Save the source and selected output; record original Forge commit, model files, prompts, seed, sampler, scheduler, steps, CFG, source and target dimensions, resize mode, denoising, fix-steps state, extensions and every result chosen for another pass.