# Anima Aesthetic 1.1 - ControlNet precise control 
 
**Creator:** AI-KSK · **Collection:** Video 279 / ten-workflow Anima Aesthetic 1.1 episode 
 
**Workflow file:** `Anima+Aesthetic+1.1｜ControlNet精准控制.json` · **Cover file:** `ChatGPT Image 2026年7月19日 12_25_56 (7).png` 
 
## What this workflow does 
 
anima-base-202605-v1.0 UNET with anima-highres-aesthetic-boost and anima-turbo-lora-v0.2, euler sampler at 30 steps, two-stage denoise 1.0 then 0.55. 
 
## How to use it 
 
Open the graph on RunningHub with invite code `rh-v1111`: https://www.runninghub.ai/post/2078701779059036161/?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;

Anima Aesthetic 1.1 - ControlNet Precision Control

02_anima-aesthetic-1-1-controlnet-precision-control.json

v1.0

<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 the active control-oriented Anima Aesthetic 1.1 graph in this batch. It is made for users who want stronger structure control than plain text-to-image while still keeping the Anima anime style. The workflow uses an Anima LLLite control path to inject guidance into the generation process, making it useful for pose, layout, depth-like structure, edge influence, or composition experiments depending on the prepared control input. Compared with the simpler baseline workflow, this one is better when the scene needs a specific body direction, framing, or visual layout. 
 
The inspected graph uses `anima-base-202605-v1.0.safetensors`, Qwen Image CLIP, Qwen Image HDR VAE, and an active `anima-highres-aesthetic-boost.safetensors` LoRA. The control route includes `Anima-LLLite/anima-lllite-any-test-like-v2.safetensors` through AnimaLLLiteApply. The sampling structure uses 30-step passes, with a first pass around CFG 3.0 and a second lower-denoise refinement around 0.55 and CFG around 2.88. A 3:4 resolution selector and 1.5x latent upscale stage are present. The prompt text contains a 16:9 phrase, but the connected size nodes point to 3:4, so this preview follows the actual graph structure rather than the prompt wording. 
 
Main features: 
 
- Control-focused Anima Aesthetic 1.1 workflow 
- Active Anima LLLite control injection 
- Active highres aesthetic boost LoRA 
- Qwen Image CLIP text encoder 
- Qwen Image HDR VAE route 
- 30-step controlled generation pass observed 
- Lower-denoise refinement pass observed 
- 3:4 composition support through connected size nodes 
- 1.5x latent upscale stage in the graph 
- Useful for pose, layout, and composition control tests 
- Turbo LoRA is present but bypassed 
- Technical copy follows connected nodes, not prompt-only aspect words 
 
Suggested workflow: 
 
Prepare a clean control input first, then write a prompt that supports the same pose and scene rather than fighting it. If the image follows the control too loosely, increase control influence gradually. If it becomes rigid or loses aesthetic quality, reduce control strength and let the refinement pass recover detail. Keep the control image simple when testing new prompts. 
 
⚙️ RunningHub Workflow 
 
Try the workflow online right now — no installation required. 
👉 Workflow: https://www.runninghub.ai/post/2078374978801905666?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/2078374978801905666?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 ControlNet Workflow

<div data-youtube-video="https://youtu.be/ShiAjBa8EXc"></div> 
 
This workflow is the active control-oriented Anima Aesthetic 1.1 graph in this batch. It is made for users who want stronger structure control than plain text-to-image while still keeping the Anima anime style. The workflow uses an Anima LLLite control path to inject guidance into the generation process, making it useful for pose, layout, depth-like structure, edge influence, or composition experiments depending on the prepared control input. Compared with the simpler baseline workflow, this one is better when the scene needs a specific body direction, framing, or visual layout. 
 
The inspected graph uses `anima-base-202605-v1.0.safetensors`, Qwen Image CLIP, Qwen Image HDR VAE, and an active `anima-highres-aesthetic-boost.safetensors` LoRA. The control route includes `Anima-LLLite/anima-lllite-any-test-like-v2.safetensors` through AnimaLLLiteApply. The sampling structure uses 30-step passes, with a first pass around CFG 3.0 and a second lower-denoise refinement around 0.55 and CFG around 2.88. A 3:4 resolution selector and 1.5x latent upscale stage are present. The prompt text contains a 16:9 phrase, but the connected size nodes point to 3:4, so this preview follows the actual graph structure rather than the prompt wording. 
 
Main features: 
 
- Control-focused Anima Aesthetic 1.1 workflow 
- Active Anima LLLite control injection 
- Active highres aesthetic boost LoRA 
- Qwen Image CLIP text encoder 
- Qwen Image HDR VAE route 
- 30-step controlled generation pass observed 
- Lower-denoise refinement pass observed 
- 3:4 composition support through connected size nodes 
- 1.5x latent upscale stage in the graph 
- Useful for pose, layout, and composition control tests 
- Turbo LoRA is present but bypassed 
- Technical copy follows connected nodes, not prompt-only aspect words 
 
Suggested workflow: 
 
Prepare a clean control input first, then write a prompt that supports the same pose and scene rather than fighting it. If the image follows the control too loosely, increase control influence gradually. If it becomes rigid or loses aesthetic quality, reduce control strength and let the refinement pass recover detail. Keep the control image simple when testing new prompts. 
 
⚙️ RunningHub Workflow 
 
Try the workflow online right now — no installation required. 
👉 Workflow: https://www.runninghub.ai/post/2078374978801905666?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/2078374978801905666?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。

Files with SHA256: 12630776093fa3ad3ad70065d919a9a79a9a318ed3ecd6bbd89201b56b193791