플러그인

DeepSeek Harness(DSH)를 위한 통합 이미지 생성 라우터: 모든 OpenAI 호환 엔드포인트에서 이미지 모델을 자동 발견하고, draw_image 및 draw_list_sources 도구를 제공하며, SenseNova, StepFun, Agnes, Qwen, Flux, SD, Imagen 등을 지원한다.

DeepSeek Harness용 Agnes AI 이미지 및 비디오 생성 플러그인.

AI image and video studio as a floating DSH panel, so creation runs alongside the conversation instead of replacing it: text-to-image, image-to-image and multi-image composition at 1K-4K across eight aspect ratios; text-to-video and image-to-video with first-frame control at 4-12 seconds; short-drama mode that imports a script (.txt/.md/.json), breaks it into storyboard shots for preview and batch generation; and a prompt-expert workspace. Zero runtime dependencies.

Optimized fork of dsh-image-gen with batch generation (count), gallery pagination, lazy loading, fetch retry/timeout, and 7 providers: Gemini/OpenAI/Seedream/DashScope/Agnes/GLM-Image/Stability AI.

OAuth sign-in for 9 subscription LLM providers (Claude, Codex, Grok, Antigravity, OpenRouter, Agnes AI, Qwen, Spark, ERNIE) with zero-config login and usage dashboards.

Agnes AI image & video generation tools for DSH (agnes_image_generate / agnes_video_generate)

DeepSeek Harness용 대화형 UI/UX 시각 리뷰 플러그인: 모든 OpenAI 호환 멀티모달 엔드포인트(예: agnes-2.5-flash) 기반의 vision_review / vision_ask 도구