# Anima Aesthetic 1.1 - DMDX 4-step speed run 
 
**Creator:** AI-KSK · **Collection:** Video 279 / ten-workflow Anima Aesthetic 1.1 episode 
 
**Workflow file:** `Anima+Aesthetic+1.1｜DMDX+四步极速版.json` · **Cover file:** `ChatGPT Image 2026年7月19日 12_25_56 (8).png` 
 
## What this workflow does 
 
anima-base-202605-v1.0 + anima-turbo-lora-v0.2 + dmdx_student_final_comfy, ModelSamplingAuraFlow, 4 steps at CFG 1 with er_sde. 
 
## How to use it 
 
Open the graph on RunningHub with invite code `rh-v1111`: https://www.runninghub.ai/post/2078701772113272834/?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 - DMDX 4-Step Speed Run

03_anima-aesthetic-1-1-dmdx-4-step-speed-run.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 fast Anima Aesthetic 1.1 variant built around a DMDX four-step generation route. It is meant for rapid iteration rather than maximum-detail final rendering. If you need to test many prompt ideas, preview character concepts, or quickly compare composition directions, this graph gives you a much shorter sampling path while still keeping the Anima-style anime output direction. It is especially useful before moving a successful prompt into the three-stage render or 1.5x upscale workflow for a more polished final pass. 
 
The inspected JSON uses `anima-base-202605-v1.0.safetensors`, Qwen Image CLIP, Qwen Image HDR VAE, and an active `dmdx_student_final_comfy.safetensors` LoRA. The sampler route is clearly built around 4 steps with CFG around 1 and er_sde/simple style settings. The graph uses a 1:1 square resolution selector and a 1024 x 1024 empty latent path. An Anima Turbo LoRA appears in the file, but it is bypassed, so this description does not present it as part of the active chain. The main promise is speed: use this workflow to explore ideas quickly, then upscale or refine the best outputs elsewhere. 
 
Main features: 
 
- Fast DMDX workflow for Anima Aesthetic 1.1 
- Active DMDX student LoRA route 
- Four-step sampler path observed 
- Low CFG setup for fast distilled generation 
- Qwen Image CLIP text encoder 
- Qwen Image HDR VAE path 
- 1:1 square composition support 
- 1024 x 1024 latent setup observed 
- Good for prompt exploration and idea testing 
- Useful before moving results into high-quality workflows 
- Turbo LoRA is present but bypassed 
- Designed for quick online trials through RunningHub 
 
Suggested workflow: 
 
Use short, clear prompts and treat this as a speed preview workflow. Generate several seeds quickly, pick the strongest composition, then move that prompt or image into the three-stage render, image-to-image, or upscale workflow. If the result looks under-detailed, do not force this graph to behave like a high-step renderer; use it to find the idea, then refine elsewhere. 
 
⚙️ RunningHub Workflow 
 
Try the workflow online right now — no installation required. 
👉 Workflow: https://www.runninghub.ai/post/2078374958207700993?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/2078374958207700993?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 DMDX Four-Step

<div data-youtube-video="https://youtu.be/ShiAjBa8EXc"></div> 
 
This workflow is the fast Anima Aesthetic 1.1 variant built around a DMDX four-step generation route. It is meant for rapid iteration rather than maximum-detail final rendering. If you need to test many prompt ideas, preview character concepts, or quickly compare composition directions, this graph gives you a much shorter sampling path while still keeping the Anima-style anime output direction. It is especially useful before moving a successful prompt into the three-stage render or 1.5x upscale workflow for a more polished final pass. 
 
The inspected JSON uses `anima-base-202605-v1.0.safetensors`, Qwen Image CLIP, Qwen Image HDR VAE, and an active `dmdx_student_final_comfy.safetensors` LoRA. The sampler route is clearly built around 4 steps with CFG around 1 and er_sde/simple style settings. The graph uses a 1:1 square resolution selector and a 1024 x 1024 empty latent path. An Anima Turbo LoRA appears in the file, but it is bypassed, so this description does not present it as part of the active chain. The main promise is speed: use this workflow to explore ideas quickly, then upscale or refine the best outputs elsewhere. 
 
Main features: 
 
- Fast DMDX workflow for Anima Aesthetic 1.1 
- Active DMDX student LoRA route 
- Four-step sampler path observed 
- Low CFG setup for fast distilled generation 
- Qwen Image CLIP text encoder 
- Qwen Image HDR VAE path 
- 1:1 square composition support 
- 1024 x 1024 latent setup observed 
- Good for prompt exploration and idea testing 
- Useful before moving results into high-quality workflows 
- Turbo LoRA is present but bypassed 
- Designed for quick online trials through RunningHub 
 
Suggested workflow: 
 
Use short, clear prompts and treat this as a speed preview workflow. Generate several seeds quickly, pick the strongest composition, then move that prompt or image into the three-stage render, image-to-image, or upscale workflow. If the result looks under-detailed, do not force this graph to behave like a high-step renderer; use it to find the idea, then refine elsewhere. 
 
⚙️ RunningHub Workflow 
 
Try the workflow online right now — no installation required. 
👉 Workflow: https://www.runninghub.ai/post/2078374958207700993?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/2078374958207700993?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: 204f3b6124d18a2296f6d5f62e07537c719b24acb46871ca863888ce68cd6d0a