Image AI Tools

While LCM and Turbo have unlocked near real-time image diffusion, the quality is still a bit lacking. TCD on the other hand manages to generate images with both clarity and detailed intricacy without compromising on speed.

OHTA can create detailed and usable hand avatars from just one image. It allows for text-to-avatar conversion and editing of hand textures and shapes, using data-driven hand priors to improve accuracy with limited input.

Multi-LoRA Composition focuses on the integration of multiple Low-Rank Adaptations (LoRAs) to create highly customized and detailed images. The approach is able to generate images with multiple elements without fine-tuning and without losing detail or image quality.

Visual Style Prompting can generate images with a specific style from a reference image. Compared to other methods like IP-Adapter and LoRAs, Visual Style Prompting is better at retainining the style of the referenced image while avoiding style leakage from text prompts.

Continuous 3D Words is a control method that can modify attributes in images with a slider based approach. This allows for more control over illumination, non-rigid shape changes (like wings), and camera orientation for instance.

SEELE can move around objects within an image. It does so by removing it, inpainting occluded portions and harmonizing the appearance of the repositioned object with the surrounding areas.

StableIdentity is a method that can generate diverse customized images in various contexts from a single input image. The cool thing about this method is, that it is able to combine the learned identity with ControlNet and even inject it into video (ModelScope) and 3D (LucidDreamer) generation.

pix2gestalt is able to estimate the shape and appearance of whole objects that are only partially visible behind occlusions.

Depth Anything is a new monocular depth estimation method. The model is trained on 1.5M labeled images and 62M+ unlabeled images, which results in impressive generalization ability.

InstantID is a ID embedding-based method that can be used to personalize images in various styles using just a single facial image, while ensuring high fidelity.

PIA is a method that can animate images generated by custom Stable Diffusion checkpoints with realistic motions based on a text prompt.

Intrinsic Image Diffusion can generate detailed albedo, roughness, and metallic maps from a single indoor scene image.

DiffusionLight can estimate the lighting in a single input image and convert it into an HDR environment map. The technique is able to generate multiple chrome balls with varying exposures for HDR merging and can be used to seamlessly insert 3D objects into an existing photograph. Pretty cool.

ControlNet-XS can control text-to-image diffusion models like Stable Diffusion and Stable Diffusion-XL with only 1% of the parameters of the base model. It is about twice as fast as ControlNet and produces higher quality images with better control.

PhotoMaker can generate realistic human photos from input images and text prompts. It can change attributes of people, like changing hair colour and adding glasses, turn people from artworks like Van Gogh’s self-portrait into realistic photos, or mix identities of multiple people.

DPM-Solver can generate high-quality samples from diffusion probabilistic models in just 10 to 20 function evaluations. It is 4 to 16 times faster than previous methods and works with both discrete-time and continuous-time models without extra training.

AmbiGen can generate ambigrams by optimizing letter shapes for clear reading from two angles. It improves word accuracy by over 11.6% and reduces edit distance by 41.9% on the 500 most common English words.

Readout Guidance can control text-to-image diffusion models using lightweight networks called readout heads. It enables pose, depth, and edge-guided generation with fewer parameters and training samples, allowing for easier manipulation and consistent identity generation.

X-Adapter can enable pretrained plugins like ControlNet and LoRA from Stable Diffusion 1.5 to work with the SDXL model without retraining. It adds trainable mapping layers for feature remapping and uses a null-text training strategy to improve compatibility and functionality.

Custom Diffusion can quickly fine-tune text-to-image diffusion models to generate new variations from just a few examples in about 6 minutes on 2 A100 GPUs. It allows for the combination of multiple concepts and requires only 75MB of storage for each additional model, which can be compressed to 5-15MB.