AI Art Weekly
ꜩ Collect Cover

Subscribe to our newsletter

AI Art Weekly #129

Hello, my fellow dreamers, and welcome to issue #129 of AI Art Weekly! πŸ‘‹

It’s been two slow summer weeks. Aside from Grok 4 and a few interesting papers, there hasn’t been that much β€œbig” news. The coolest update this week came from HuggingFace. They announced Reach Mini, an open-source robot that you can code yourself. Pretty cool, definitely going to get one for Mini-Tulpa when it releases.

Personally, I’m still addicted to Midjourney and growing my Promptcache collection with new V7 style codes while pounding away at my day job projects. Enjoy your summer, dreamers! ✌️

PROMPTCACHE

Support the newsletter and unlock the full potential of AI-generated art with my curated collection of 325+ high-quality Midjourney SREF codes and 3000+ creative prompts.

promptcache.com
PROMPTCACHE

News & Papers

3D

OmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesion

Arxiv, Project Page, Demo

OmniPart can generate 3D objects from a single image by planning their structure and then creating them.

OmniPart example

DreamArt: Generating Interactable Articulated Objects from a Single Image

Arxiv, Project Page

DreamArt can create detailed 3D objects from a single image.

DreamArt example

Image

ReFlex: Text-Guided Editing of Real Images in Rectified Flow via Mid-Step Feature Extraction and Attention Adaptation

Arxiv, Project Page, Code

ReFlex can change the high-level features of an image based on a text prompt while keeping its main structure.

ReFlex example

Depth Anything at Any Condition

Arxiv, Project Page, Code

Depth Anything at Any Condition can estimate depth from a single image in different lighting and weather conditions.

Depth Anything at Any Condition example

SketchColour: Channel Concat Guided DiT-based Sketch-to-Colour Pipeline for 2D Animation

Arxiv, Project Page, Code

SketchColour can turn 2D animation sketches into fully colored frames.

SketchColour example

Calligrapher: Freestyle Text Image Customization

Arxiv, Project Page, Code

Calligrapher can customize text images with artistic typography and a style injection framework.

Calligrapher example

Video

Tora2: Motion and Appearance Customized Diffusion Transformer for Multi-Entity Video Generation

Arxiv, Project Page, Code

Tora2 can generate videos with customized motion and appearance for multiple entities.

Tora2 example

LongAnimation: Long Animation Generation with Dynamic Global-Local Memory

Arxiv, Project Page, Code

LongAnimation can create long-term animations with consistent colors.

LongAnimation example

GaVS: 3D-Grounded Video Stabilization via Temporally-Consistent Local Reconstruction and Rendering

Arxiv, Project Page, Code

GaVS can stabilize videos by reconstructing and rendering them in 3D.

GaVS example

CanonSwap: High-Fidelity and Consistent Video Face Swapping via Canonical Space Modulation

Arxiv, Project Page, Code (coming soon)

CanonSwap can transfer identities from images to videos while keeping natural movements like head poses and facial expressions.

CanonSwap example

JAM-Flow: Joint Audio-Motion Synthesis with Flow Matching

Arxiv, Project Page

JAM-Flow can create facial motion and speech together in one system. It uses special modules for motion and audio, and it works with text and audio inputs to generate synchronized talking head videos and animations.

JAM-Flow example

OmniVCus: Feedforward Subject-driven Video Customization with Multimodal Control Conditions

Arxiv, Project Page, Code (coming soon)

OmniVCus can customize videos by allowing changes based on depth, masks, and text prompts.

OmniVCus example

Audio

Hear-Your-Click: Interactive Video-to-Audio Generation via Object-aware Contrastive Audio-Visual Fine-tuning

Arxiv, Code

Hear-Your-Click can generate specific sounds for objects in videos when users click on them. It improves the connection between sound and visuals, allowing for precise audio that matches user-selected objects.

Hear-Your-Click example

ThinkSound: Chain-of-Thought Reasoning in Multimodal Large Language Models for Audio Generation and Editing

Arxiv, Project Page, Code, Demo

ThinkSound can generate sound from video either with a caption or Chain-of-Thought.

ThinkSound example

Enjoy your summer my fellow dreamers! Hushed Loomlight style is now on Promptcache.

And that my fellow dreamers, concludes yet another AI Art weekly issue. If you like what I do, you can support me by:

  • Sharing it πŸ™β€οΈ
  • Following me on Twitter: @dreamingtulpa
  • Buying me a coffee (I could seriously use it, putting these issues together takes me 8-12 hours every Friday πŸ˜…)
  • Buying my Midjourney prompt collection on PROMPTCACHE πŸš€
  • Buying access to AI Art Weekly Premium πŸ‘‘

Reply to this email if you have any feedback or ideas for this newsletter.

Thanks for reading and talk to you next week!

– dreamingtulpa

by @dreamingtulpa