This workflow is the tiled upscale option for Anima Aesthetic 1.1 images. It is designed for cases where a single generated image needs to be enlarged while preserving detail across larger areas. Instead of only doing a latent upscale, the graph includes a pixel-upscale model and tile-based image processing, which is better suited for larger output preparation. It is useful for finished character art, posters, wallpaper crops, and images where you want more visible detail in hair, costume edges, background texture, and line work.

The inspected workflow uses an Anima base route, Qwen Image CLIP, Qwen Image HDR VAE, and a connected upscale section with `4x_NMKD-Siax_200k.pth`, ImageUpscaleWithModel, ImageScaleToTotalPixels, TTP image tile batching, tile sizing, and tiled VAE decode. The tile blocks are important because they allow the workflow to process larger images in manageable regions rather than pushing everything through one large pass. Some LoRA nodes appear in the file but are bypassed, so this Civitai copy focuses on the active upscale and tiling structure. Compared with the 1.5x latent upscale workflow, this one is more clearly aimed at post-generation enlargement.

Main features:

- Tiled upscale workflow for Anima Aesthetic 1.1 images
- 4x_NMKD-Siax upscale model observed
- ImageUpscaleWithModel route
- Tile-based image batching
- Tile sizing and tiled decode support
- Qwen Image CLIP text encoder
- Qwen Image HDR VAE path
- Useful for larger final images and posters
- Better suited for post-generation enlargement than pure txt2img
- Helps preserve detail across larger surfaces
- Bypassed LoRAs are not advertised as active
- Good companion to the baseline and three-stage workflows

Suggested workflow:

Start with a clean source image. Avoid feeding heavily broken hands or faces into the upscale stage, because tiling can enlarge defects as well as details. If the upscaled result shows tile boundaries or inconsistent texture, lower aggressive scaling choices and test smaller regions first. Use this workflow after the image is already compositionally strong, not as the first step in prompt exploration.

⚙️ RunningHub Workflow

Try the workflow online right now — no installation required.
👉 Workflow: https://www.runninghub.ai/post/2078374969167417346?inviteCode=rh-v1111

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

🎁 Fan Benefits: Register to get 1000 points + daily login 100 points — enjoy 4090 performance and 48 GB super power!

📺 Bilibili Updates (Mainland China & Asia-Pacific)

If you’re in the Asia-Pacific region, you can watch the video below to see the workflow demonstration and creative breakdown.
📺 Bilibili Video: https://www.bilibili.com/video/BV1xJKB6vEfp/

☕ Support Me on Ko-fi

If you find my content helpful and want to support future creations, you can buy me a coffee ☕.
Every bit of support helps me keep creating — just like a spark that can ignite a blazing flame.
👉 Ko-fi: https://ko-fi.com/aiksk

💼 Business Contact

For collaboration or inquiries, please contact aiksk95 on WeChat.

⚙️打开下方链接即可在线体验，无需安装。
👉 工作流： https://www.runninghub.ai/post/2078374969167417346?inviteCode=rh-v1111
如果觉得效果理想，你也可以在本地进行自定义部署。

🎁 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： https://www.bilibili.com/video/BV1xJKB6vEfp/

我会在 夸克网盘 持续更新模型资源：
👉 https://pan.quark.cn/s/20c6f6f8d87b
这些资源主要面向本地用户，方便进行创作与学习。