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
18 shown of 37,470
bad-image-v2-39000
Not my TI. The original is from
Xavier from Love and Deepspace [IllustriousXL]
Reviews, Hearts, Likes etc. are very appreciated!
asatsuki fgfff style (Pokemon Trainer Artwork style)
UPDATE 6/20/25: THIS MODEL MIGHT DISAPPEAR IN THE NEXT FEW WEEKS! More information at:
Nemotron 3.5 ASR Streaming 0.6B CoreML INT8
Cache-aware streaming Conformer + RNN-T from NVIDIA, ported to CoreML (.mlmodelc) for on-device inference on Apple Silicon. 600 M params, 40 language-locales, native punctuation and capitalization. INT8 palettized...
Rebekka Larsson MXAI
Rebekka was trained using only prompts, no humans involved and not a single image.
Light and shadow composition for illustriousXL
Enhance the light and composition to a certain extent
Gogo Bomango (Bomango) [PONYXL] Character LyCORIS
☑️If you like my work, leave a review. I really appreciate them!✍️
Talene from AFK Arena [IllustriousXL]
Reviews, Hearts, Likes etc. are very appreciated!
Psyger-0 (shangri-la frontier)
Trained on 44 images from the anime. Used frames of the anime to train it.
Kazuma Ikezawa (Summer Wars)
A LoHa trained on 8 images of Kazuma Ikezawa.
Young Petelgeuse Romaneeconti (Re:Zero)
Trained on 85 images from the anime. Used frames of the anime to train it.
DimWitDog Style [Anima]
Style of DimWitDog for Anima. My first LoRA. @dimwitdog is a keyword.
Rich Creamery Butter [Illustrious]
Then we top it off with bacon, ham, and a fried egg.
Charlie Keats MXAI
Charlie is a lovely girl who doesn't exist
V67 Synthography
V67 Synthography - A Cinematic LoRA for Krea 2
Gemma 4 26B A4B It GGUF
> [!IMPORTANT] > This model is automatically converted using
Inja no kuruwa (style)
I would recommend these settings for generating:
Pixel Art Anime LoRA (DoRA) AnimagineXLV3.1&4
DoRA is trained on images of pixel art by artist Brodall Pixel (The dataset consists of 46 images).
