This is a high-speed anime illustration generation application based on Anima base model + Anima Turbo LoRA + Qwen Image text encoding + Two-stage eight-step sampling + Latent upscale refinement. Users only need to input an anime scene prompt. The system first generates a base image through the first-stage 8-step sampling, then enhances the image size via Latent 1.5x upscale, and finally adds details using the second-stage 8-step refinement sampling, quickly generating complete anime illustrations in low steps.
The core advantages of this workflow are: fast generation speed, strong anime texture, suitable for landscape covers and batch generation. Compared to standard high-step anime generation, it reduces sampling costs via Turbo LoRA and compensates for detail loss using a second-stage latent upscale. It is ideal for quickly creating Bilibili covers, Xiaohongshu anime images, character posters, fantasy illustrations, ACG key visuals, and video cover assets. When using it, it is recommended to focus on controlling three items: positive prompts determine the content, aspect ratio determines the cover purpose, and random seed determines the variations.
🎁Claim RH Coins first, then try the workflow! Click the avatar in the top right corner → Invitation Code → Enter [rh-v1111] to instantly receive 1000 RH Coins, and log in daily to get another 100 RH Coins~ For more ComfyUI workflows, tutorials, and gameplay, please follow our official WeChat account (AIKSK), with simultaneous updates on Douyin / Bilibili / Xiaohongshu / YouTube (AI-KSK) ✨


No creations yet

No creations available.