This model is a fine-tuned version of openai/whisper-large-v3 on the Custom Libyan Arabic podcast — 258 manually transcribed clips dataset. It achieves the following results on the evaluation set: Loss: 0.5756 Wer:...

Text modelopenai/whisper-large-v3

Status

Listed

ModelHugging Face

Ps4mas Grpo 9b Fullft Smoke Best

Run label: grpo9bfullftsmoke06240657 Checkpoint kind: best Global step: 2 Eval reward mean: -1.067 Training state: see trainingstate.json / checkpointbest.json in run dir

Text modelQwen/Qwen3.5-9B9B

Status

Verified

ModelHugging Face

Hy MT2 7B GGUF

🖥️ Official Website | 💬 GitHub | 🪡 AngelSlim | 📚 Hy-MT2 Report

Othertencent/Hy-MT2-7B7B

Status

Verified

ModelExternal source

qwen_image_edit_2511_int8_convrot.safetensors

NewBie-Image-Exp0.1-bf16.safetensors

CuteCaption | UltraInsta - The Ultimate Influencer Character Creation Solution

For Krea2 no noising strategies used... Sigmoid, ProdigyPlus, Rank 78, trained on pixel areas: 512 - 768 - 1024 - 1280 - 1328

Long Tongue - ZIB and ZIT

Generates images of woman with long tongues.

Luna Shirakawa (白河月愛) - Our Dating Story: The Experienced You and The Inexperienced Me

luna shirakawa, long hair, blue eyes, blonde hair, hair ornament, bow, multicolored hair, hairclip,

loraStable Diffusion 1.5

Status

Listed

ModelExternal source

Octane Render

A LoRA that expands on the built-in “ Octane Render ” style found in most models. Its core is cinematic hyper-detail, beautiful lighting, glossy surfaces, and finely rendered features. It leans toward close-up...

Brekkist (Artist Style) [PonyXL/Illustrious]

Revisited the dataset. Some new images, but mostly the same. Different trigger word to avoid style bleed since IL knows some artists kinda.

[SDXL] Artist Style: chongzhen

SDXL LoRA/LyCORIS works best on the model that it was trained on. I will release multiple versions for a few popular models. Feel free to request for artist or model.