Text-to-video AI models: generate video from text prompts. Wan 2.2 TI2V 5B in GGUF — efficient open weights for local text & image to video.
🤝 Open to Collab
Gönke Lorenzen
Goenzilla
AI & ML interests
Graphic Design, HTML, Imagery, Videos, AI - Curating open AI models on Hugging Face 🤗 — image-to-image (img2img), image & video editing, ControlNet, 3D, audio. Start here: Image-to-Image Collection https://huggingface.co/collections/Goenzilla/image-to-image
Recent Activity
liked a model about 2 hours ago
microsoft/Florence-2-large updated a collection 8 days ago
image to video updated a collection 8 days ago
Text to imageOrganizations
None yet
Image-to-video AI models: turn still images into video with LTX-Video distilled, Wan 2.2 workflows & more. Compare the best img2video models.
Meta SAM Segment Anything models for zero-shot image segmentation, object detection, audio segmentation & visual understanding.
Audio & music generation AI: Audio2Face 3D, music transformers. Perfect for sound synthesis, audio processing & AI music creation.
ControlNet models for structure control: Z-Image Turbo ControlNet, ControlNet Union SDXL, FLUX ControlNet. Ideal for pose, depth & canny.
-
alibaba-pai/Z-Image-Turbo-Fun-Controlnet-Union-2.1
Updated • 104k • 467 -
xinsir/controlnet-union-sdxl-1.0
Text-to-Image • 1B • Updated • 177k • 1.87k -
Shakker-Labs/FLUX.1-dev-ControlNet-Union-Pro-2.0
Text-to-Image • 2B • Updated • 17.9k • 469 -
thibaud/controlnet-openpose-sdxl-1.0
Text-to-Image • Updated • 64.4k • 441
AI image editing & generation: Qwen Image Edit & Qwen Image for image-to-image & text-to-image. Perfect for computer vision & generative AI.
-
Qwen/Qwen-Image-Edit
Image-to-Image • 20B • Updated • 137k • • 2.57k -
Qwen/Qwen-Image
Text-to-Image • 20B • Updated • 324k • • 2.69k -
fal/Qwen-Image-Edit-2511-Multiple-Angles-LoRA
Image-to-Image • Updated • 74.9k • • 1.61k -
black-forest-labs/FLUX.2-klein-4B
Image-to-Image • 4B • Updated • 428k • • 1.08k
Curated image-to-image (img2img) AI models on Hugging Face for editing & style transfer: FLUX.2, HunyuanImage 3.0, Qwen LoRAs. Compare & download.
-
black-forest-labs/FLUX.2-dev
Image-to-Image • 32B • Updated • 332k • • 2.49k -
black-forest-labs/FLUX.2-klein-4B
Image-to-Image • 4B • Updated • 428k • • 1.08k -
black-forest-labs/FLUX.2-klein-9B
Image-to-Image • 9B • Updated • 169k • • 1.78k -
black-forest-labs/FLUX.2-klein-base-9B
Image-to-Image • 9B • Updated • 90k • • 422
Image-text-to-text models (VLMs): multimodal AI that reads images and answers in text. Featuring Kimi K2.5 — more models added regularly.
Top LoRAs for ComfyUI: Pixel Art, Anime, Logo Design, FLUX effects. Perfect for style transfer, character design & creative workflows.
-
Shakker-Labs/FLUX.1-dev-LoRA-Logo-Design
Text-to-Image • Updated • 487 • • 404 -
tarn59/pixel_art_style_lora_z_image_turbo
Text-to-Image • Updated • 14.5k • • 58 -
UmeAiRT/FLUX.1-dev-LoRA-Modern_Pixel_art
Text-to-Image • Updated • 802 • • 72 -
strangerzonehf/Ghibli-Flux-Cartoon-LoRA
Text-to-Image • Updated • 513 • • 39
Transform sketches into images: ControlNet Canny, scribble models. Perfect for drawing, edge detection & line art to image.
Text-to-3D & image-to-3D AI models: meshes, textures & spatial AI assets from prompts or photos - TRELLIS.2, Hunyuan3D, SAM 3D & more.
Qwen Image-Layered: revolutionary text-to-image generation with layered synthesis. Perfect for generative AI & computer vision.
Text-to-video AI models: generate video from text prompts. Wan 2.2 TI2V 5B in GGUF — efficient open weights for local text & image to video.
Curated image-to-image (img2img) AI models on Hugging Face for editing & style transfer: FLUX.2, HunyuanImage 3.0, Qwen LoRAs. Compare & download.
-
black-forest-labs/FLUX.2-dev
Image-to-Image • 32B • Updated • 332k • • 2.49k -
black-forest-labs/FLUX.2-klein-4B
Image-to-Image • 4B • Updated • 428k • • 1.08k -
black-forest-labs/FLUX.2-klein-9B
Image-to-Image • 9B • Updated • 169k • • 1.78k -
black-forest-labs/FLUX.2-klein-base-9B
Image-to-Image • 9B • Updated • 90k • • 422
Image-to-video AI models: turn still images into video with LTX-Video distilled, Wan 2.2 workflows & more. Compare the best img2video models.
Image-text-to-text models (VLMs): multimodal AI that reads images and answers in text. Featuring Kimi K2.5 — more models added regularly.
Meta SAM Segment Anything models for zero-shot image segmentation, object detection, audio segmentation & visual understanding.
Top LoRAs for ComfyUI: Pixel Art, Anime, Logo Design, FLUX effects. Perfect for style transfer, character design & creative workflows.
-
Shakker-Labs/FLUX.1-dev-LoRA-Logo-Design
Text-to-Image • Updated • 487 • • 404 -
tarn59/pixel_art_style_lora_z_image_turbo
Text-to-Image • Updated • 14.5k • • 58 -
UmeAiRT/FLUX.1-dev-LoRA-Modern_Pixel_art
Text-to-Image • Updated • 802 • • 72 -
strangerzonehf/Ghibli-Flux-Cartoon-LoRA
Text-to-Image • Updated • 513 • • 39
Audio & music generation AI: Audio2Face 3D, music transformers. Perfect for sound synthesis, audio processing & AI music creation.
Transform sketches into images: ControlNet Canny, scribble models. Perfect for drawing, edge detection & line art to image.
ControlNet models for structure control: Z-Image Turbo ControlNet, ControlNet Union SDXL, FLUX ControlNet. Ideal for pose, depth & canny.
-
alibaba-pai/Z-Image-Turbo-Fun-Controlnet-Union-2.1
Updated • 104k • 467 -
xinsir/controlnet-union-sdxl-1.0
Text-to-Image • 1B • Updated • 177k • 1.87k -
Shakker-Labs/FLUX.1-dev-ControlNet-Union-Pro-2.0
Text-to-Image • 2B • Updated • 17.9k • 469 -
thibaud/controlnet-openpose-sdxl-1.0
Text-to-Image • Updated • 64.4k • 441
Text-to-3D & image-to-3D AI models: meshes, textures & spatial AI assets from prompts or photos - TRELLIS.2, Hunyuan3D, SAM 3D & more.
AI image editing & generation: Qwen Image Edit & Qwen Image for image-to-image & text-to-image. Perfect for computer vision & generative AI.
-
Qwen/Qwen-Image-Edit
Image-to-Image • 20B • Updated • 137k • • 2.57k -
Qwen/Qwen-Image
Text-to-Image • 20B • Updated • 324k • • 2.69k -
fal/Qwen-Image-Edit-2511-Multiple-Angles-LoRA
Image-to-Image • Updated • 74.9k • • 1.61k -
black-forest-labs/FLUX.2-klein-4B
Image-to-Image • 4B • Updated • 428k • • 1.08k
Qwen Image-Layered: revolutionary text-to-image generation with layered synthesis. Perfect for generative AI & computer vision.