feat(anima): add img2img capability (#13903)

[Paramveersingh-S]

Description
Fixes #13903 by bringing img2img capabilities to the Anima modular pipeline.

Since Anima utilizes the new Modular Pipelines architecture, this PR adds the necessary, custom modular steps and orchestrates them into a core img2img denoise block:

• AnimaProcessImagesInputStep: Custom input processor block added to properly resize and format image latent dependencies.
• AnimaVaeEncoderStep: Utilizes AutoencoderKLQwenImage to encode preprocessed PIL image tensors, managing internal scaling factors (latents_mean/latents_std).
• AnimaImg2ImgSetTimestepsStep & AnimaImg2ImgPrepareLatentsStep: Calculates timesteps via the strength parameter offset and adds FlowMatchEulerDiscreteScheduler noise to image latents.
• Registers the img2img pipeline map under AnimaImg2ImgAutoBlocks.

This enables users to run image-to-image translations using Anima while acting as a great reference implementation for the new modular pipeline structure!

Checklist

• All modular pipeline blocks initialize smoothly.
• Code conforms to the new diffusers modular block standards.

[github-actions]

Hi @Paramveersingh-S, thanks for the PR! It does not appear to link an issue it fixes. If this PR addresses an existing issue, please add a closing keyword (e.g. Fixes #1234) to the PR description so the issue is linked. See the contribution guide for more details. If this PR intentionally does not fix a tracked issue, a maintainer can add the no-issue-needed label to silence this reminder.