전체 검색

AI 모델 85003

• RetNet-0.5B↗

  Ayaka157

• dreamgen_lucid-v1-nemo-GGUF↗

  bartowski

• LatitudeGames_Wayfarer-Large-70B-Llama-3.3-GGUF↗

  bartowski

• Nemomix-v4.0-12B-GGUF↗

  bartowski

  No chat template specified so default is used. This may be incorrect, check original model card for details. If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run: The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.

• MrBERT-es↗

  BSC-LT

• krea2-identity-edit↗

  conradlocke

  ☕ **Support on Ko-fi** — all tips go straight to GPU compute for future versions. 🧰 **Training code is public:** krea2edit-trainer — the ai-toolkit extension these LoRAs were trained with, geometry-matched to the nodes, with measured consumer-GPU VRAM requirements. > **V2 ships as two LoRAs:** > > - **`krea2_identity_edit_v2.safetensors` — Krea 2 Identity Edit V2.** Put a person > from one photo into any scene, pose, outfit and lighting. Extremely improved > likeness, better sharpness and skin/fabric texture, and far more freedom to > restage than v1.2. > - **`krea2_general_edit_v2.safetensors` — Krea 2 General Edit V2.** Instruction-based > editing: remove, recolor, relight, swap backgrounds, add objects, change text and > outfits, restyle, flat lays. > > **License:** free for personal / non-commercial use; commercial use needs a > license from me, case by case — see License. > > **Use one LoRA per task** — they share a lineage, so loading both at full strength > breaks the image (see Using both). > > **Requires the V2 nodes** (`comfyui-krea2edit` ≥ 2.0.0), which add **reference > placement**: choose per reference whether it is pinned onto the output layout or > placed beside it — e.g. keep a scene exactly while placing a person freely in it. > > **Low-VRAM versions:** `..._v2_r128.safetensors` (0.91GB) and `..._v2_r64.safetensors` (0.46GB) > for both LoRAs — rank-reduced from the full files, near-identical quality. > > Prior versions remain available (`..._v1_2*`, `..._v1_1*`, `..._v1`).

• DFM-Mimir↗

  danish-foundation-models

• Qwen3.8-27B-MLX-Serve-4bit↗

  ddalcu

• google.gemma-3n-E2B-it-GGUF↗

  DevQuasar

• GLM-5.3-Flash-oQ8e-mtp↗

  dfp-official