Watch the full video first if you want to understand how this Anima Edit workflow works in practice. The video shows how Anima Base can be used for image editing, local inpainting, outfit change, and reference-guided transformation, while keeping the workflow online and easy to test without rebuilding the full ComfyUI environment locally.
This ComfyUI workflow is designed for Anima image editing and local transformation. Its main purpose is to take an existing image, define the edit direction through prompt and mask logic, then regenerate the target area while preserving the original image structure as much as possible. Instead of using Anima only for pure text-to-image generation, this workflow turns Anima into a practical editing pipeline for changing clothes, adjusting appearance, modifying a scene, testing character edits, and comparing different edit LoRA routes.
The workflow is built around anima_baseV10.safetensors as the main model. It uses qwen_3_06b_base.safetensors as the text encoder and qwen_image_vae.safetensors as the VAE. The input image is loaded through LoadImage, then resized to a controlled 1024×1024 working canvas. This gives the editing process a stable base resolution and avoids random size mismatch problems.
A key part of the workflow is the IC-style side-by-side editing structure. AILab_ICLoRAConcat combines the original image and edit target into a left-right layout, producing both an image and a base mask. This structure helps the model understand that the right side should become the edited result while the left side provides the original reference. The workflow also uses InpaintModelConditioning to prepare positive conditioning, negative conditioning, latent image, image pixels, and mask data for local inpainting.
The workflow includes Anima-LLLite inpainting v2 through AnimaLLLiteApply. This module injects lightweight inpainting guidance into the Anima model, helping the model follow the image and mask more accurately during local edits. It is especially useful when the target is not to redraw the whole image, but to change a selected area while keeping identity, pose, framing, and background logic more stable.
The graph also includes two edit LoRA routes: AnimaEditV1 and lora_edit_ZeroTwo. These are loaded through LoraLoaderModelOnly and connected into separate generation branches. This makes the workflow useful for testing different Anima editing behaviors. One route can be used for general Anima Edit experiments, while another can be used for a more specific edit style or clothing-change behavior. The workflow also applies Cosmos Reference latent logic through ApplyCosmosReferenceLatent, which helps preserve reference structure during the edit process.
Compared with ordinary image-to-image workflows, this graph is more specialized for Anima-based editing. A basic img2img workflow may change too much or fail to understand the target edit. This workflow combines mask-aware conditioning, IC-style layout, LLLite inpainting guidance, edit LoRA branches, reference latent control, and prompt template replacement, making it better for controlled transformations.
This workflow is suitable for outfit change, local character editing, anime image repair, style-consistent edits, before/after comparison images, masked inpainting tests, clothing experiments, character concept revision, RunningHub demonstrations, and Civitai workflow publishing.
Main features:
Anima Base image editing workflow
Local inpainting and image transformation
anima_baseV10.safetensors main model route
Qwen 3 0.6B text encoder
Qwen Image VAE decoding
Anima-LLLite inpainting v2 guidance
AnimaEditV1 edit LoRA route
lora_edit_ZeroTwo edit LoRA route
AILab_ICLoRAConcat side-by-side edit layout
InpaintModelConditioning mask-aware editing
ApplyCosmosReferenceLatent reference preservation
Prompt template replacement system
Multiple edit branches for comparison
PreviewImage output for fast inspection
Suggested workflow:
Prepare a clean source image first. The subject should be clear, and the area you want to edit should not be too small or heavily blocked. Load the image into the workflow, then write a direct edit prompt such as changing clothing, changing accessories, adjusting the scene, or modifying a selected visual feature. Use the IC-style layout and mask conditioning to define the edit target. Start with the Anima-LLLite inpainting route first to check whether the mask and edit direction are correct. Then compare the AnimaEditV1 and lora_edit_ZeroTwo branches to see which route gives better identity preservation and cleaner transformation. If the edit changes too much, simplify the prompt and strengthen reference consistency. If the edit is too weak, make the target instruction more explicit.
⚙️ RunningHub Workflow
Try the workflow online right now — no installation required.
👉 Workflow: https://www.runninghub.ai/post/2060760904450535425?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/2060760904450535425?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。