全站搜索

AI 模型 85003

• JackChew_-_Qwen2-VL-2B-OCR-gguf↗

  RichardErkhov

• lamm-mit_-_PRefLexOR_ORPO_DPO_EXO_REFLECT_10222024-gguf↗

  RichardErkhov

• DeepSeek-V4.1-Flash-Abliterated↗

  securepeak

• average_word_embeddings_komninos↗

  sentence-transformers

• Asclepius-Llama2-7B↗

  starmpcc

• switchboard-router-0.5b-ONNX↗

  switchboardllm

• Qwen3.8-27B-FP8-block-AWQ↗

  TelperionAI

• Mistral-7B-Instruct-v0.2-DARE-GGUF↗

  TheBloke

• SG-Raccoon-Yi-55B-GGUF↗

  TheBloke

• refcontrol-FLUX.2-klein-9B-reference-pose-lora↗

  thedeoxen

  A LoRA for **FLUX.2 Klein 9B Base** that fuses a **reference image** (identity) with a **pose control map** (skeleton / keypoints). It preserves **identity and style** from the reference while following the **body pose and structure** from the pose map. Each preview is a **single combined image** from ComfyUI: **Pose → Reference → Result** (left to right). This LoRA was primarily trained on **humans**, but it also works with **stylized characters** and some objects. Its main purpose is to **preserve identity** — facial features, hairstyle, clothing, or object details — from the reference image, while adapting the subject to the **pose and skeleton structure** defined by the control map.