Anima Base Text-to-Image + ControlNet Face & Hand Repair Workflow

This workflow is designed for Anima Base text-to-image generation with ControlNet-style structure guidance, face refinement, and hand repair. Its main purpose is to let creators start from a pure text prompt, generate an anime-style image through Anima Base, use structure control to improve composition stability, and then automatically refine the most failure-prone areas: the face, eyes, hands, and fingers.

Unlike a basic text-to-image workflow, this setup is not only a single-pass image generator. It combines Anima Base generation, Qwen image text encoding, empty latent creation, prompt-guided sampling, NAG guidance, ControlNet / Anima LLLite-style structure control, latent upscaling, second-pass refinement, face detection, SAM-assisted facial repair, hand detection, hand segmentation, FaceDetailer repair, preview nodes, and final image output. This makes it more suitable for creators who want a complete anime image production pipeline rather than a simple prompt-to-picture graph.

The workflow uses anima_baseV10.safetensors as the main Anima Base model route, qwen_3_06b_base.safetensors as the text encoder, and qwen_image_vae.safetensors as the VAE. It also includes CLIPSetLastLayer, EmptyLatentImage, CLIPTextEncode, NAGuidance, AnimaLLLiteApply, AIO_Preprocessor, ClownsharKSampler_Beta, LatentUpscaleBy, VAEDecode, FaceDetailer, SAMLoader, UltralyticsDetectorProvider, and multiple preview nodes. This structure shows that the workflow is built for text-to-image generation plus controlled refinement.

The first generation stage starts from an empty latent image, meaning the image is created from text rather than from an existing input image. The positive prompt describes the target anime key visual, such as an adult anime beauty, celestial fantasy scene, long platinum hair, luminous skin, floating palace balcony, colossal sky dragon, clouds, wind, sunlight, and cinematic scale contrast. The negative prompt suppresses low quality, blurry output, JPEG artifacts, low resolution, and other weak-image problems.

A key part of the workflow is the ControlNet-style guidance route. The workflow includes a reference image path, DepthAnything preprocessing, and Anima LLLite application. This allows the creator to use structure guidance while still generating from text. In practical terms, this helps the output keep stronger pose, depth, silhouette, layout, and spatial composition instead of relying only on the text prompt. For anime key visual generation, this is useful because pure text-to-image generation can easily drift in character placement, body structure, perspective, or background scale.

The workflow also includes NAG guidance. This helps strengthen prompt adherence and improve control during generation. For complex fantasy scenes with one character, giant creatures, dramatic lighting, and large-scale composition, stronger guidance is useful because the model needs to balance subject clarity, background scale, and visual style.

The generation process uses a staged route. After the first sampling pass, the workflow can upscale the latent result and run a second refinement pass. This is important because a first-pass image may already have a strong composition, but details such as face clarity, clothing texture, hair, lighting, and background sharpness often need extra refinement. Latent upscaling improves the image before final decoding, making the result more suitable for high-quality preview images, cover images, and Civitai showcases.

The face repair section uses face detection and SAM-based refinement to locate the face area and run a focused detail pass. This helps improve facial symmetry, eye clarity, expression quality, and local anime rendering detail without forcing the whole image to regenerate. For character images, this is one of the most important post-generation steps because a strong full-body image can still fail if the face is soft or distorted.

The hand repair section uses dedicated hand detection and segmentation models, including hand_yolov8s and PitHandDetailer-style segmentation. This part is designed to identify hand regions, crop them, refine them, and paste the repaired result back into the full image. It helps reduce extra fingers, fused fingers, malformed hands, weak palms, broken gestures, and unclear finger structure.

This workflow is ideal for anime text-to-image generation, Anima Base character creation, fantasy key visual production, ControlNet-style composition control, high-quality anime illustration generation, automatic face repair, automatic hand repair, Civitai preview images, RunningHub demos, and social media cover artwork.

If you want to see how Anima Base, text-to-image generation, ControlNet-style structure guidance, NAG enhancement, latent upscale refinement, face detection, hand detection, SAM refinement, and final detail repair work together in one practical pipeline, watch the full tutorial from the YouTube link above.

⚙️ Try the Workflow Online

👉 Workflow: the link above to run the workflow directly online and view the generation results in real time.

If the results meet your expectations, you can also deploy it locally for further customization.

🎁 Fan Benefits: Register now to get 1000 points, plus 100 daily login points — enjoy 4090-level performance and 48 GB of powerful compute!

📺 Bilibili Updates (Mainland China & Asia-Pacific)

If you are in Mainland China or the Asia-Pacific region, you can watch the video below for workflow demos and a detailed creative breakdown.

📺 Bilibili Video: will continue updating model resources on Quark Drive:

👉 resources are mainly prepared for local users, making creation and learning more convenient.

⚙️ 在线体验工作流

👉 工作流： 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： 夸克网盘 持续更新模型资源：

👉