A F5-TTS fine-tuned for Spanish
DPO-SDXL Canny controlnet with LoRA support.
Run inpainting with Flux, compatible with Canny ControlNet, LoRAs and HyperFlux_8step
UPDATE: new upscaling algorithm for a much improved image quality. Fermat.app open-source implementation of an efficient ControlNet 1.1 tile for high-quality upscales. Increase the creativity to encourage hallucination.
Very fast img2img for a collaboration with AI in real time
A better alternative to SDXL refiners, providing a lot of quality and detail. Can also be used for inpainting or upscaling.
Restyle an image with the style of another one. I strongly suggest to upscale the results with Clarity AI
Better than SDXL at both prompt adherence and image quality, by dataautogpt3
RunDiffusion FX Photorealistic model, developed by RunDiffusion.
ControlNet implementation for RunDiffusion's PhotorealisticFX model.
Photorealistic FX by RunDiffusion with LoRA integrated. Works as good or better than RealisticVision.
'''Last update: Now supports img2img.''' SDXL Canny controlnet with LoRA support.
Good old controlnet + inpaint + lora
Great image quality, good old SDXL with a new and improved Tile refiner.
An extremely fast all-in-one model to use LCM with SDXL, ControlNet and custom LoRA url's!
An improved outpainting model that supports LoRA urls. This model uses PatchMatch to improve the mask quality.
SDXL with prompt weighting available using Compel's syntax. Check the Github link for the docs.
This model is cold. You'll get a fast response if the model is warm and already running, and a slower response if the model is cold and starting up.
