FramePack Video Generation
Collection
fast & compact video generation with FramePack - a next-frame prediction neural network structure that generates videos progressively β’ 7 items β’ Updated β’ 6
AI Tools for Art - April & May '25
Tools & models from the upcoming 4rd issue of AI Tools for Art π read more: https://open.substack.com/pub/multimodalaiart
-
-
ByteDance/DreamO
Updated β’ 100 -
DreamO
π¨598A Unified Framework for Image Customization
-
DreamO: A Unified Framework for Image Customization
Paper β’ 2504.16915 β’ Published β’ 24 -
ICEdit
πΌ662Universal Image Editing is worth a single LoRA
-
stepfun-ai/Step1X-Edit
Image-to-Image β’ Updated β’ 121 β’ 330 -
Step1X Edit
π»361Edit an image based on the given instruction.
-
stepfun-ai/Step1X-3D
Updated β’ 106 -
Step1X 3D
π¨247image2mesh
-
tencent/HunyuanVideo-Avatar
Image-to-Video β’ Updated β’ 328 -
tencent/HunyuanCustom
Image-to-Video β’ Updated β’ 191 -
tencent/HunyuanPortrait
Image-to-Video β’ Updated β’ 75 -
Chroma
π₯248Generate detailed fantasy and realistic images from text descriptions
-
lodestones/Chroma
Text-to-Image β’ Updated β’ 1.34k -
ostris/Flex.2-preview
Text-to-Image β’ Updated β’ 513 β’ 390 -
Kijai/WanVideo_comfy
Updated β’ 6.35M β’ 2.28k -
Wan2.1 Fast
π₯1.61kGenerate a video from an image with a prompt
-
ACE-Step/ACE-Step-v1-3.5B
Text-to-Audio β’ Updated β’ 727 -
ACE Step
π»659A Step Towards Music Generation Foundation Model
-
DeepSite Gallery
π931Browse apps made with DeepSite
-
HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation
Paper β’ 2505.04512 β’ Published β’ 36 -
ByteDance-Seed/BAGEL-7B-MoT
Any-to-Any β’ 15B β’ Updated β’ 9.85k β’ 1.2k -
BAGEL
π216Demo for BAGEL
-
EasyControl Ghibli
π¦1.45kNew Ghibli EasyControl model is now released!!
-
EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer
Paper β’ 2503.07027 β’ Published β’ 29 -
EasyControl
π¦78Huggingface demo of EasyControl
-
Blip 3o
π¨83BLIP 3o any-to-any
-
BLIP3o/BLIP3o-Model-8B
Updated β’ 870 β’ 101 -
showlab/OmniConsistency
Image-to-Image β’ Updated β’ 224 β’ 121 -
OmniConsistency
π215Generate styled image from reference image and external LoRA
-
OmniConsistency: Learning Style-Agnostic Consistency from Paired Stylization Data
Paper β’ 2505.18445 β’ Published β’ 63 -
PlayHT/PlayDiffusion
Updated β’ 110 -
PlayDiffusion
π¨119Generate modified audio from text and voice
-
ResembleAI/chatterbox
Text-to-Speech β’ Updated β’ 1.78M β’ β’ 1.56k -
Chatterbox TTS
πΏ1.73kExpressive Zeroshot TTS
