Diretório de recursos
Encontre o que você precisa para seu fluxo de trabalho.
Guides: techniques, setup, and troubleshootingPesquise Sweet Tea Pipes, fluxos de trabalho externos, modelos, pacotes de nós e guias em um catálogo vinculado a evidências.
Comece com um fluxo de trabalho em vez disso ↗Resultados da pesquisa
Todos os recursos
20 exibido of 42.665
Manga Bubbles Detect
YOLOv8 model for detecting speech bubbles in manga pages. Trained to locate bubble bounding boxes (single class location-of-bubbles).
jasperai_Flux.1-dev-Controlnet-Upscaler_fp8.safetensors
Corona Timir | Magical Girl Lyrical Nanoha ViVid | 魔法少女リリカルなのはViVid
Lora-scale: 0.7-0.9 Trigger Words : corona timir, long hair, brown hair, blue eyes
Entropy Trpo Weights
PyTorch checkpoints for the comparative study in A Review of Entropy-Based Extensions to Trust Region Policy Optimization.
Efficientnet B5 Coco 256x192
A 2D human pose estimation model trained at DeKUT-DSAIL using the MMPose framework. Predicts 17 COCO keypoints from a single cropped person image.
Darwin 28B KOREA I1 GGUF
For a convenient overview and download list, visit our model page for this model.
Siglip2 Giant Opt Patch16 384 Kor 16384
This model is a 14.75% smaller version of google/siglip2-giant-opt-patch16-384 optimized for Korean language via vocabulary size reduction using the trimming method. This trimmed model should perform similarly to the...
Add music to a video
Generate a soundtrack from your video's content and receive a video combining that music with the original audio. For a first run, upload a video containing an audio track and lasting no more than six minutes. Leave Music prompt empty to let Sonilo rely entirely on the video, or describe the soundtrack you want. Run with the existing gain and export defaults, then listen to the result and adjust the two audio levels as needed. Original audio volume and Music volume independently adjust the tracks in decibels before they are added together. Both default to +1 dB; 0 dB leaves a track unchanged, positive values raise its level and negative values lower it. The input must still contain audio even when its level is reduced. Adding tracks can increase the combined level, so lower their gains if the mix sounds overloaded. The result uses the source video's frames and frame rate. Advanced Video output controls select the container, codec and encoder CRF; leave these at their defaults for a first run. The graph also saves generated music separately before the Music volume adjustment, without the original audio. Advanced Music export controls select FLAC, MP3 or Opus; the supplied MP3 configuration offers V0, 128k and 320k quality settings. Sonilo currently ignores seed, so this tool does not offer reproducible generation through a seed setting.
Sft Oasst1 Gpt Oss 120b As Qwen3.6 35b A3b Seed42
Dementor imitation (disguise) LoRA adapter — dataset oasst1, seed 42.
Aarokira Style - Pony / Anima
jgY_ex78eEFhuhwHSIjyi_pytorch_lora_weights.safetensors
兰梦琴 Lan Mengqin.safetensors
MAD GOD《Style》
Trained on 129 images (HD screenshots mostly) from Phil Tippet's Mad God film.
Fire Emblem GBA Sprite Style [Illustrious]
Fire Emblem GBA Sprite Style. Trained on Illustrious-XL.
May (ハルカ) - Pokemon (ポケモン)
pokemonmay, blue eyes, brown hair, bandana, long hair, red bandana, twintails, hair between eyes,
Elise from Assassin's Creed Unity [IllustriousXL]
! I'm not training specific outfits !
FinAI
Meridian.AI is a finance-specialized language model that continuously fine-tunes a Qwen2.5-0.5B backbone every hour on 25+ finance and math datasets, using Elastic Weight Consolidation (EWC) to prevent catastrophic...
Kawaii Goddess: Monica
This is an embedding of a woman that I've generated consistent faces of thru SD and decided to make into an embedding for easier access in the future. It uses a mere 5 tokens.
