Anima Preview3 | Local Redraw & Inpainting Workflow

This workflow is designed for Anima Preview3 inpainting and local redraw, focusing on controlled partial editing inside an existing anime image. Its main purpose is to let creators mask a specific region, describe the desired change, and regenerate only that local area while keeping the rest of the image stable, coherent, and visually consistent.

The workflow uses anima-preview3-base.safetensors as the main generation model, qwen_3_06b_base.safetensors as the text encoder, and qwen_image_vae.safetensors as the VAE. It combines image loading, mask input, mask expansion, blurred mask blending, latent encoding, Differential Diffusion, prompt generation, sampling, VAE decoding, preview, and final saving into one practical local-editing pipeline. Compared with a normal image-to-image workflow, this setup is more suitable when you do not want to redraw the whole image. You only want to modify one selected area.

The key part of this workflow is the inpainting mask route. The source image is loaded with its mask, then passed through image_scale_pixel_v2 to normalize the image and mask into a model-friendly size. The mask is then processed by GrowMaskWithBlur, which expands and softens the selected area. This is important because hard mask edges often create visible seams, while a slightly expanded and blurred mask gives the model enough transition space to blend the new content naturally into the original image.

The workflow then uses VAEEncode to convert the source image into latent space and SetLatentNoiseMask to restrict the repainting area. This means the sampler is guided to focus on the masked region instead of freely changing the entire frame. The DifferentialDiffusion node further strengthens this local redraw behavior, making the workflow more suitable for precise anime inpainting, object replacement, facial adjustment, hairstyle changes, clothing fixes, prop replacement, and small composition corrections.

Another important feature is the built-in prompt-generation logic. The workflow includes an LLM API prompt engineer node, using a role instruction specialized for anime inpainting and partial redraw. It analyzes the reference image, understands the overall composition, art style, lighting, pose, environment, and visual tone, then converts the user’s short edit instruction into a single English prompt line. This is useful because local redraw prompts need to be more careful than normal generation prompts. They must describe the new area while preserving the rest of the image.

The example instruction in the workflow is “only modify the specified region: change the head into a pineapple.” This shows the intended usage clearly: the user provides a short local edit request, the LLM rewrites it into a model-friendly inpainting prompt, and Anima Preview3 performs the masked redraw while maintaining the original image identity, style, lighting, and surrounding details.

The sampling stage uses ClownsharKSampler_Beta with a 30-step beta57 setup, CFG around 3, and a full local redraw denoise setting. This gives the masked region enough freedom to change while the unmasked area remains protected by the mask and latent structure. The negative prompt suppresses common anime-generation issues such as low quality, blurry output, bad hands, malformed limbs, duplicated elements, deformed faces, text, and watermark artifacts.

This workflow is ideal for creators who need a clean Anima Preview3 local redraw setup for fixing details, replacing objects, editing character parts, modifying accessories, repairing small visual problems, testing funny local transformations, or preparing polished Civitai preview images. If you want to see how the mask, LLM prompt rewrite, Differential Diffusion, Anima Preview3 model, and final inpainting output work together, watch the full tutorial from the YouTube link above.

⚙️ Try the Workflow Online

👉 Workflow: the link above to run the workflow directly online and view the generation results in real time.

If the results meet your expectations, you can also deploy it locally for further customization.

🎁 Fan Benefits: Register now to get 1000 points, plus 100 daily login points — enjoy 4090-level performance and 48 GB of powerful compute!

📺 Bilibili Updates (Mainland China & Asia-Pacific)

If you are in Mainland China or the Asia-Pacific region, you can watch the video below for workflow demos and a detailed creative breakdown.

📺 Bilibili Video: will continue updating model resources on Quark Drive:

👉 resources are mainly prepared for local users, making creation and learning more convenient.

⚙️ 在线体验工作流

👉 工作流： 粉丝福利： 注册即送 1000 积分，每日登录 100 积分，畅玩 4090 体验 48 G 超级性能！

📺 Bilibili 更新（中国大陆及南亚太地区）

如果你在中国大陆或南亚太地区，可以通过下方视频查看该工作流的实测效果与构思讲解。

📺 B站视频： 夸克网盘 持续更新模型资源：

👉