text-to-image 3

Unified static-image generation router for DeepSeek Harness: one image_generate tool with standard parameters, config-driven OpenAI-compatible engine routing (OpenAI Images, Zhipu CogView, and any compatible endpoint) with health-aware fallback, durable w

Image generation for DeepSeek Harness: a generate_image tool with pluggable providers — the FAL queue, any OpenAI-compatible images API, or a ChatGPT/Grok subscription with no API key at all. The picture is shown inline in the conversation; the model rece

Universal vision bridge for DeepSeek Harness: pick how images are processed — auto-rewrite via a vision LLM, explicit tools, or hybrid. Multi-channel endpoint (DSH catalog / OpenAI-compatible / Ollama / custom), LRU description cache, settings card with c