REVIEW 14 cited by
$\lambda$-ECLIPSE: Multi-Concept Personalized Text-to-Image Diffusion Models by Leveraging CLIP Latent Space
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
abstract
Despite the recent advances in personalized text-to-image (P-T2I) generative models, it remains challenging to perform finetuning-free multi-subject-driven T2I in a resource-efficient manner. Predominantly, contemporary approaches, involving the training of Hypernetworks and Multimodal Large Language Models (MLLMs), require heavy computing resources that range from 600 to 12300 GPU hours of training. These subject-driven T2I methods hinge on Latent Diffusion Models (LDMs), which facilitate T2I mapping through cross-attention layers. While LDMs offer distinct advantages, P-T2I methods' reliance on the latent space of these diffusion models significantly escalates resource demands, leading to inconsistent results and necessitating numerous iterations for a single desired image. In this paper, we present $\lambda$-ECLIPSE, an alternative prior-training strategy that works in the latent space of a pre-trained CLIP model without relying on the diffusion UNet models. $\lambda$-ECLIPSE leverages the image-text interleaved pre-training for fast and effective multi-subject-driven P-T2I. Through extensive experiments, we establish that $\lambda$-ECLIPSE surpasses existing baselines in composition alignment while preserving concept alignment performance, even with significantly lower resource utilization. $\lambda$-ECLIPSE performs multi-subject driven P-T2I with just 34M parameters and is trained on a mere 74 GPU hours. Additionally, $\lambda$-ECLIPSE demonstrates the unique ability to perform multi-concept interpolations.
Forward citations
Cited by 14 Pith papers
-
DSH-Bench: A Difficulty- and Scenario-Aware Benchmark with Hierarchical Subject Taxonomy for Subject-Driven Text-to-Image Generation
DSH-Bench supplies a hierarchical 58-category subject set, difficulty/scenario labels, and a human-aligned SICS metric that exposes systematic failures of 19 subject-driven T2I models.
-
DreamCache: Finetuning-Free Lightweight Personalized Image Generation via Feature Caching
DreamCache achieves zero-shot personalized image generation by caching reference features from one denoising step and injecting them through 25M-parameter adapters.
-
Large-Scale Text-to-Image Model with Inpainting is a Zero-Shot Subject-Driven Image Generator
Diptych Prompting generates images of a reference subject in new contexts by framing the task as text-conditioned inpainting of the right panel of a two-panel image, with no fine-tuning.
-
FreeCus: Free Lunch Subject-driven Customization in Diffusion Transformers
FreeCus is a training-free method that combines pivotal attention sharing, reversed noise shifting, and MLLM captions to personalize Flux.1 text-to-image generation from a single reference image.
-
RefEdit: A Benchmark and Method for Improving Instruction-based Image Editing Model on Referring Expressions
RefEdit-Bench measures referring-expression image editing; the RefEdit model, trained on 20K synthetic triplets, reports state-of-the-art results over million-scale baselines.
-
ComposeAnyone: Controllable Layout-to-Human Generation with Decoupled Multimodal Conditions
ComposeAnyone generates human images by conditioning a diffusion model on hand-drawn color-block layouts together with decoupled text or reference-image descriptions for each body part.
-
SC-Pro: Training-Free Framework for Defending Unsafe Image Synthesis Attack
A training-free voting defense, SC-Pro, detects adversarial NSFW prompts by checking images generated from perturbed inputs, with a distilled one-step variant for speed.
-
Object-level Visual Prompts for Compositional Image Generation
VisualComposer combines coarse and fine image features in cross-attention, plus inference-time guidance, to generate diverse multi-object scenes from per-object visual prompts.
-
PatchDPO: Patch-level DPO for Finetuning-free Personalized Image Generation
PatchDPO scores each image patch by similarity to a reference and retrains personalized generators with patch-weighted losses, reporting higher DINO and CLIP-I on DreamBench than prior finetuning-free methods.
-
Steering Rectified Flow Models in the Vector Field for Controlled Image Generation
FlowChef enables training-free, inversion-free, backprop-free controlled generation for rectified flow models by replacing the gradient through the model with the direct loss gradient on the estimated clean image.
-
Create Anything Anywhere: Layout-Controllable Personalized Diffusion Model for Multiple Subjects
A tuning-free framework that jointly preserves multiple reference subject identities and obeys bounding-box layout constraints in text-to-image diffusion.
-
Personalized Text-to-Image Generation with Auto-Regressive Models
A two-stage fine-tuning strategy enables the auto-regressive Lumina-mGPT 7B model to personalize image generation from 3-5 reference images, reaching DreamBooth-comparable fidelity on Dreambench.
-
Personalized Multimodal Large Language Models: A Survey
The paper provides a survey and taxonomy of personalization techniques for multimodal LLMs across text generation, image generation, recommendation, and retrieval.
-
FBI: Learning Dexterous In-hand Manipulation with Dynamic Visuotactile Shortcut Policy
The abstract claims a new visuotactile robot manipulation policy (FBI) that outperforms baselines, but the manuscript body is an unrelated paper on text-to-image synthesis, so the claimed result is absent.
Discussion (0). Continue with ORCID to comment.