Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
Google: Gemma 4 31B (free)
ModelsGemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
google/gemma-4-31b-it:free -
Qwen-Image-2.1-viggle-turbo
Modelstext to image model by Viggle · diffusers
Viggle/Qwen-Image-2.1-viggle-turbo -
primal_vae
Modelsmodel by ostris · diffusers
ostris/primal_vae -
Wan2.1-VACE-14B
Modelsimage to video model by Wan-AI · diffusers
Wan-AI/Wan2.1-VACE-14B -
Chroma
Modelstext to image model by lodestones · pytorch
lodestones/Chroma -
HunyuanDiT
Modelsmodel by Tencent-Hunyuan · hunyuan-dit
Tencent-Hunyuan/HunyuanDiT -
image to image model by ScottzillaSystems · diffusers
ScottzillaSystems/qwen-image-edit-plus-nsfw-lora -
Fibo-2.0
Modelsimage to image model by Comfy-Org · diffusion-single-file
Comfy-Org/Fibo-2.0 -
Google: Gemma 4 26B A4B
ModelsGemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...
google/gemma-4-26b-a4b-it -
ACE-Step-v1-3.5B
Modelstext to audio model by ACE-Step · diffusers
ACE-Step/ACE-Step-v1-3.5B -
BFS-Best-Face-Swap-Video
Modelsimage to video model by Alissonerdx · diffusers
Alissonerdx/BFS-Best-Face-Swap-Video -
Hunyuan3D-2.1
Modelsimage to 3d model by tencent · hunyuan3d-2
tencent/Hunyuan3D-2.1 -
model by Felldude · diffusers
Felldude/MiniMaxImage_hdr_diffusers_vae -
FastH3-Omni-Comfy
Modelsmodel by FastVideo · diffusion-single-file
FastVideo/FastH3-Omni-Comfy -
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...
google/gemma-4-26b-a4b-it:free -
MOSS-Image-SFT-4-steps
Modelstext to image model by akhaliq · diffusers
akhaliq/MOSS-Image-SFT-4-steps -
text to image model by Noctaluna · diffusion-single-file
Noctaluna/Noct-Q-Uncensored-Qwen-Image-2.1 -
Diffusion-Qwen3.8-27B
Modelstext generation model by summerAIO · transformers
summerAIO/Diffusion-Qwen3.8-27B -
Idol
Modelsimage to 3d model by Comfy-Org · diffusion-single-file
Comfy-Org/Idol -
controlnet-openpose-sdxl-1.0
Modelstext to image model by xinsir · diffusers
xinsir/controlnet-openpose-sdxl-1.0 -
void-model
Modelsvideo to video model by netflix
netflix/void-model -
chroma-h3
Modelstext to image model by lodestones · diffusers
lodestones/chroma-h3 -
NitroFusion2
Modelstext to image model by ChenDY · diffusion-single-file
ChenDY/NitroFusion2 -
Wan2.2-I2V-A14B
Modelsimage to video model by Wan-AI · wan2.2
Wan-AI/Wan2.2-I2V-A14B
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.