Watch the full video first if you want to understand how this Anima HiresFix workflow works in practice. The video shows how Anima Base can generate a 1024 image first, then use a 1.5x latent refinement stage to improve detail, structure, and final image quality without making the workflow overly complex.

This ComfyUI workflow is designed for Anima Base 1.0 high-resolution refinement using a classic HiresFix-style two-stage generation route. Its main purpose is to create a stable 1024×1024 base image first, then upscale the latent to 1536×1536 and run a second controlled refinement pass. Compared with a simple one-pass Anima generation workflow, this structure gives the final image more detail, cleaner linework, better texture density, and stronger overall polish.

The workflow is built around anima_baseV10.safetensors as the main model. After loading the model, ModelSamplingAuraFlow applies a shift value of 3, preparing the Anima model for the intended sampling behavior. The text side uses qwen_3_06b_base.safetensors as the text encoder with the stable_diffusion type setting. The output is decoded with qwen_image_vae.safetensors, which keeps the workflow aligned with the Anima / Qwen Image VAE ecosystem.

The first generation stage uses an EmptyLatentImage at 1024×1024 with batch size 1. The positive prompt defines the image direction, while the negative prompt suppresses low-quality output, weak score tags, blurry artifacts, JPEG artifacts, and unwanted artist-name artifacts. The first KSampler is configured as the base sample stage, using 34 steps, CFG 4.5, er_sde sampler, simple scheduler, and denoise 1. This stage is responsible for building the main composition, character structure, pose, lighting, and global visual identity.

After the base latent is generated, the workflow sends it into LatentUpscale. The upscale method is bicubic, and the target size is 1536×1536, which is exactly a 1.5x increase from the original 1024 base. This is important because it improves the working resolution without jumping too aggressively into an unstable size. A moderate 1.5x latent upscale is often easier to control than a larger upscale when the goal is refinement rather than complete regeneration.

The second KSampler performs the HiresFix refinement stage. It uses 18 steps, CFG 4.5, er_sde sampler, simple scheduler, and denoise 0.35. The lower denoise value means the workflow keeps the original composition from the first stage while adding more detail and cleaner high-resolution structure. This stage is where the image gains sharper eyes, cleaner edges, better fabric texture, stronger lighting detail, and a more finished look.

Compared with ordinary Anima text-to-image generation, this workflow is better for final image polishing. A one-pass workflow is faster, but it may leave the result slightly soft or under-detailed. This HiresFix workflow is more suitable when the first image already looks correct and you want to enhance it instead of completely changing it.

This workflow is suitable for anime character illustrations, high-resolution portraits, fantasy characters, clean lineart images, social media covers, Civitai previews, RunningHub showcases, and any Anima image that needs a controlled 1.5x quality upgrade.

Main features:

• Anima Base 1.0 HiresFix workflow

• 1024×1024 base generation

• 1.5x latent upscale to 1536×1536

• anima_baseV10.safetensors main model route

• Qwen 3 0.6B text encoder

• Qwen Image VAE decoding

• ModelSamplingAuraFlow with shift 3

• First-stage base sampling

• Second-stage high-resolution refinement

• er_sde sampler with simple scheduler

• CFG 4.5 controlled generation

• Refine denoise 0.35 for structure preservation

• Clean two-stage image polish pipeline

• Native SaveImage output

Suggested workflow:

Start with a clear prompt that defines the character, subject, style, lighting, composition, and final visual direction. Run the 1024×1024 base stage first and check whether the image structure is correct. Do not rely on the HiresFix stage to fix a bad composition. If the base image is wrong, adjust the prompt and regenerate. Once the base result is stable, use the 1.5x latent upscale stage and run the second sampler with denoise 0.35. If the refined image changes too much, lower the denoise slightly. If the result is too soft, keep the structure but strengthen detail wording in the prompt. Use this workflow when you want Anima output that feels more finished than a simple draft.

⚙️ RunningHub Workflow

Try the workflow online right now — no installation required.
👉 Workflow: https://www.runninghub.ai/post/2060759010810355714?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/BV1GmVS6hEzu/

☕ 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/2060759010810355714?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/BV1GmVS6hEzu/

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。