Some of the relevant (July/2026) language base models on Hugging Face (meaning, LLMs trained on pure text, without Instruct/SFT/RLHF/RL tuning etc)
Apolinário from multimodal AI art PRO
multimodalart
AI & ML interests
ML + art and creativity
Recent Activity
updated a Space 13 minutes ago
hugging-apps/chess-reasoning-llm published a Space 15 minutes ago
hugging-apps/chess-reasoning-llm liked a model about 7 hours ago
Glint-Research/Glint-2Organizations
A curated set of amazing Stable Diffusion XL LoRAs (they power the LoRA the Explorer Space)
All text-to-image open source base models, with their respective license
Openly licensed dataset with allowed commercial usage
Wan 2.2 release collection
Pipelines for Perturbed Attention Guidance with 🧨 library
-
Perturbed-Attention Guidance SDXL
🌀128Generate AI images with and without Perturbed‑Attention Guidance
-
multimodalart/sdxl_perturbed_attention_guidance
Unconditional Image Generation • Updated • 72 -
jyoung105/sdxl_perturbed_attention_guidance_i2i
Updated • 4 -
jyoung105/sdxl_perturbed_attention_guidance_controlnet
Updated
-
lllyasviel/control_v11p_sd15_inpaint
Image-to-Image • 0.4B • Updated • 12.9k • 133 -
lllyasviel/control_v11p_sd15_openpose
Image-to-Image • 0.4B • Updated • 12.7k • 142 -
lllyasviel/control_v11p_sd15_mlsd
Image-to-Image • 0.4B • Updated • 8.04k • 18 -
lllyasviel/control_v11p_sd15_lineart
Image-to-Image • 0.4B • Updated • 7.51k • 79
Some of the relevant (July/2026) language base models on Hugging Face (meaning, LLMs trained on pure text, without Instruct/SFT/RLHF/RL tuning etc)
Wan 2.2 release collection
Pipelines for Perturbed Attention Guidance with 🧨 library
-
Perturbed-Attention Guidance SDXL
🌀128Generate AI images with and without Perturbed‑Attention Guidance
-
multimodalart/sdxl_perturbed_attention_guidance
Unconditional Image Generation • Updated • 72 -
jyoung105/sdxl_perturbed_attention_guidance_i2i
Updated • 4 -
jyoung105/sdxl_perturbed_attention_guidance_controlnet
Updated
A curated set of amazing Stable Diffusion XL LoRAs (they power the LoRA the Explorer Space)
All text-to-image open source base models, with their respective license
-
lllyasviel/control_v11p_sd15_inpaint
Image-to-Image • 0.4B • Updated • 12.9k • 133 -
lllyasviel/control_v11p_sd15_openpose
Image-to-Image • 0.4B • Updated • 12.7k • 142 -
lllyasviel/control_v11p_sd15_mlsd
Image-to-Image • 0.4B • Updated • 8.04k • 18 -
lllyasviel/control_v11p_sd15_lineart
Image-to-Image • 0.4B • Updated • 7.51k • 79
Openly licensed dataset with allowed commercial usage