Resource directory
Find what you need for your workflow.
Guides: techniques, setup, and troubleshootingSearch Sweet Tea Pipes, external workflows, models, node packs, and guides in one evidence-linked catalog.
Start with a workflow instead ↗Search results
All resources
20 shown of 38,622
Sorjin1 LoRA
The raw LoRA adapter weights from continual pretraining of Qwen/Qwen2.5-7B on Kurdish Kurmanji academic theses.
TrueFace Adapter
This is a custom, fine-tuned version of the IP-Adapter-FaceID-PlusV2 model for Stable Diffusion 1.5. It was specifically trained to prioritize high-fidelity identity preservation while maintaining compositional...
Vjepa2 Vitl Fpc16 256 Ssv2 Uvf101
A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of VJEPA, resulting in state-of-the-art video understanding capabilities, leveraging data and model sizes at...
Quartz
Quartz is a stylized anime-oriented merge designed for crisp, vibrant linework with a slight Skorbz influence baked directly into the model. It focuses on delivering punchy colors, glossy rendering, and expressive...
Voila Base
Voila: Voi ce- La nguage Foundation Models
Whisper Small 24lang
A plain openai/whisper-small (unmodified architecture) fine-tuned on the 24 languages of the CC0 Whispered corpus. This is the matched scientific control for burakaydinofficial/whisper-small-mla-24lang — trained...
Gemma 4 E2B It Heretic Ara Q4 K M GGUF
This model was converted to GGUF format from p-e-w/gemma-4-E2B-it-heretic-ara using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.
Docubrief Qwen2.5 1.5b GGUF
For a convenient overview and download list, visit our model page for this model.
Pictory ControlNet R8 Ep10
This is the model card of a 🧨 diffusers model that has been pushed on the Hub. This model card has been automatically generated.
Rico Vit Gpt2 Finetuned
rico-vit-gpt2-finetuned is a multimodal vision-language model fine-tuned on the RICO Screen2Words dataset to generate natural language captions for mobile app UI screenshots.
PixelWave FLUX.1 Schnell 04 DF11
For more information (including how to compress models yourself), check out and
TimesNet
This project presents a hybrid architecture that replaces the temporal attention mechanism in TimeSformer with RetNet, achieving:
ControlNet Finetuning
These are controlnet weights trained on runwayml/stable-diffusion-v1-5 with new type of conditioning. You can find some example images below. prompt: there are some very tall rocks in the desert with trees prompt:...
Blip2 Opt 2.7b Roco Merged Epoch 2
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
Nanocoder v1
A 4B parameter full-stack coding assistant fine-tuned from Qwen3-4B using Unsloth + LoRA. Trained through a multi-phase pipeline with joint domain training and validation-driven checkpoint selection.
Whisper Base 24lang
A plain openai/whisper-base (unmodified architecture) fine-tuned on the 24 languages of the CC0 Whispered corpus. This is the matched scientific control for burakaydinofficial/whisper-base-mla-24lang — trained...
Wildlife Sage Grouse
Single-class detection model for Greater Sage-Grouse, fine-tuned from the Ultralytics YOLO26s backbone (pretrained on COCO).
ControlNet Floorplan
These are controlnet weights trained on stable-diffusion-v1-5/stable-diffusion-v1-5 with new type of conditioning.
Siglip2 Vision Only
This is the vision-only variant of google/siglip2-base-patch16-224, containing just the vision encoder without the text model.
Mc3 18 Hmdb51 Ucf Transfer
MC3-18 (Mixed Convolution 3D) finetuned on HMDB51 split 1 for human action recognition. This model was initialized with weights from an MC3-18 model pretrained on UCF-101 (87% accuracy) rather than Kinetics-400.
