<div data-youtube-video="https://youtu.be/ShiAjBa8EXc"><iframe src="https://www.youtube.com/embed/ShiAjBa8EXc" width="853" height="480" allowfullscreen></iframe></div> 
 
This workflow is prepared for Anima Aesthetic 1.1 text-to-image character generation with extra attention on the common weak points: faces and hands. The source name includes CN, but the inspected JSON shows the LLLite/Control-style branch is bypassed in the current file, so this Civitai preview presents the active value more accurately as a text-to-image workflow with face and hand detailer support. It is a good setup when you want direct anime character generation first, then localized repair passes to improve close-up features and hand shapes. 
 
The active graph uses `anima-base-202605-v1.0.safetensors`, Qwen Image CLIP, and Qwen Image HDR VAE. The generation route includes 30-step sampler passes, a 3:4 resolution selector, and 1.5x latent upscale stages. The detailer section includes face and hand detection resources such as `bbox/face_yolov8n.pt`, `bbox/hand_yolov8s.pt`, `segm/PitHandDetailer-v2-Test-v9c.pt`, and FaceDetailer nodes. These are the important parts for Civitai users: the workflow is not only generating an image, it also adds targeted local refinement for character features after the main render. 
 
Main features: 
 
- Text-to-image Anima Aesthetic 1.1 workflow 
- Active face detailer route 
- Active hand detector and hand refinement route 
- Qwen Image CLIP text encoder 
- Qwen Image HDR VAE decode path 
- 3:4 composition support through resolution selection 
- 30-step generation and refinement routes observed 
- 1.5x latent upscale stage in the graph 
- Useful for anime character portraits and full-body tests 
- Local repair stages help reduce face and hand artifacts 
- CN/LLLite branch is present but bypassed in this file 
- Conservative title avoids advertising inactive control nodes 
 
Suggested workflow: 
 
Begin with a prompt that clearly defines the character, pose, hands, and camera distance. Check the base generation before relying on the detailer passes. If the detailers overcorrect the face or fingers, lower their denoise or detection impact. If hands remain unstable, simplify the hand pose in the prompt, then run the detailer route again with a cleaner seed. 
 
⚙️ RunningHub Workflow 
 
Try the workflow online right now — no installation required. 
👉 Workflow: https://www.runninghub.ai/post/2078374939884212225?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 &amp; 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/2078374939884212225?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。

Anima 1.1 T2I Face Hand Detailer

<div data-youtube-video="https://youtu.be/ShiAjBa8EXc"></div> 
 
This workflow is prepared for Anima Aesthetic 1.1 text-to-image character generation with extra attention on the common weak points: faces and hands. The source name includes CN, but the inspected JSON shows the LLLite/Control-style branch is bypassed in the current file, so this Civitai preview presents the active value more accurately as a text-to-image workflow with face and hand detailer support. It is a good setup when you want direct anime character generation first, then localized repair passes to improve close-up features and hand shapes. 
 
The active graph uses `anima-base-202605-v1.0.safetensors`, Qwen Image CLIP, and Qwen Image HDR VAE. The generation route includes 30-step sampler passes, a 3:4 resolution selector, and 1.5x latent upscale stages. The detailer section includes face and hand detection resources such as `bbox/face_yolov8n.pt`, `bbox/hand_yolov8s.pt`, `segm/PitHandDetailer-v2-Test-v9c.pt`, and FaceDetailer nodes. These are the important parts for Civitai users: the workflow is not only generating an image, it also adds targeted local refinement for character features after the main render. 
 
Main features: 
 
- Text-to-image Anima Aesthetic 1.1 workflow 
- Active face detailer route 
- Active hand detector and hand refinement route 
- Qwen Image CLIP text encoder 
- Qwen Image HDR VAE decode path 
- 3:4 composition support through resolution selection 
- 30-step generation and refinement routes observed 
- 1.5x latent upscale stage in the graph 
- Useful for anime character portraits and full-body tests 
- Local repair stages help reduce face and hand artifacts 
- CN/LLLite branch is present but bypassed in this file 
- Conservative title avoids advertising inactive control nodes 
 
Suggested workflow: 
 
Begin with a prompt that clearly defines the character, pose, hands, and camera distance. Check the base generation before relying on the detailer passes. If the detailers overcorrect the face or fingers, lower their denoise or detection impact. If hands remain unstable, simplify the hand pose in the prompt, then run the detailer route again with a cleaner seed. 
 
⚙️ RunningHub Workflow 
 
Try the workflow online right now — no installation required. 
👉 Workflow: https://www.runninghub.ai/post/2078374939884212225?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 &amp; 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/2078374939884212225?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。

05_anima-1-1-t2i-face-hand-detailer.json

v1.0

# Anima Aesthetic 1.1 - Text-to-image + ControlNet + face/hand repair 
 
**Creator:** AI-KSK · **Collection:** Video 279 / ten-workflow Anima Aesthetic 1.1 episode 
 
**Workflow file:** `Anima+Aesthetic+1.1｜文生图+CN+修脸+修手+.json` · **Cover file:** `ChatGPT Image 2026年7月19日 12_25_56 (9).png` 
 
## What this workflow does 
 
60 nodes: four VAEDecode, four FaceDetailer passes, two LatentUpscaleBy stages, 30 steps euler at CFG 3 then 2.88 / denoise 0.55. 
 
## How to use it 
 
Open the graph on RunningHub with invite code `rh-v1111`: https://www.runninghub.ai/post/2078701786382290946/?inviteCode=rh-v1111 
 
The JSON is also distributed unchanged in the AI-KSK Hugging Face / ModelScope collection for this episode. Model files, LoRAs and detector weights are not bundled. 
 
## Limits 
 
Results depend on prompt, seed, sampler settings and the base model version. Third-party LoRAs keep their own licenses. No timing or quality benchmark was run for this release. 
 
## Tutorial 
 
**[Watch the complete ten-workflow YouTube tutorial](https://www.youtube.com/watch?v=ShiAjBa8EXc)** · Bilibili: https://www.bilibili.com/video/BV1xJKB6vEfp 
 
&lt;div class="data-youtube-video"&gt;&lt;iframe src="https://www.youtube.com/embed/ShiAjBa8EXc" width="560" height="315" frameborder="0" allowfullscreen&gt;&lt;/iframe&gt;&lt;/div&gt;

Files with SHA256: 29f7549f856db3399cdf8b272d9465a3284500b161259536fe35237e46c09b01