10 actions in 8 pieces of software · ranked by words, meaning and measured trust · 657 ms
modelrecord
- qwen/qwen3-7-plus
Qwen3.7-Plus is Alibaba's cost-effective multimodal model with vision-language understanding, a 1 million token context window, and strong agentic coding and tool use.
- qwen/qwen3-7-plus
modelrecord
- tool-calling
Can call tools (function calling).
- structured-outputs
Can return JSON matching a schema.
- text->text
Takes text; returns text.
- tool-calling
modelrecord
- text+image+video->text
Takes text, image, video; returns text.
- text+image+video->text
modelrecord
- text+image->text
Takes text, image; returns text.
- text+image->text
modelrecord
- qwen/qwen-image-edit-plus
The latest Qwen-Image’s iteration with improved multi-image editing, single-image consistency, and native support for ControlNet
- qwen/qwen-image-edit-plus
modelrecord
- qwen/qwen-image-edit-plus-lora
Qwen Image Edit 2509 LoRA explorer, uses HuggingFace URLs to load any safetensor
- qwen/qwen-image-edit-plus-lora
modelrecord
- qwen-edit-apps/qwen-image-edit-plus-lora-skin
Skin – Natural beauty retouch that enhances pores and tonal variation (no plastic skin) via the Skin LoRA.
- qwen-edit-apps/qwen-image-edit-plus-lora-skin
modelrecord
- qwen-edit-apps/qwen-image-edit-plus-lora-upscale
Upscale – Detail-loving upscale/restore pass that sharpens textures and color fidelity with the Upscale LoRA.
- qwen-edit-apps/qwen-image-edit-plus-lora-upscale
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.