Pith. sign in

REVIEW 3 cited by

VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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

arxiv 2204.08583 v2 pith:BYQODXMV submitted 2022-04-18 cs.CV

Katherine Crowson , Stella Biderman , Daniel Kornis , Dashiell Stander , Eric Hallahan , Louis Castricato , Edward Raff This is my paper · ORCID
classification cs.CV
keywords tasksdemonstratedomaineditingguideimageimagesopen
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Generating and editing images from open domain text prompts is a challenging task that heretofore has required expensive and specially trained models. We demonstrate a novel methodology for both tasks which is capable of producing images of high visual quality from text prompts of significant semantic complexity without any training by using a multimodal encoder to guide image generations. We demonstrate on a variety of tasks how using CLIP [37] to guide VQGAN [11] produces higher visual quality outputs than prior, less flexible approaches like DALL-E [38], GLIDE [33] and Open-Edit [24], despite not being trained for the tasks presented. Our code is available in a public repository.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 30 citations worldwide. Full citation record

  1. Video Deepfake Abuse: How Company Choices Predictably Shape Misuse Patterns

    cs.CY 2025-11 conditional novelty 6.0 of 10

    A few open-weight video models and distribution platforms dominate the creation and spread of NSFW AI video, making developer and platform choices the main intervention points for reducing non-consensual deepfake abuse.

  2. Highly Compressed Tokenizer Can Generate Without Training

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A 32-token 1D image tokenizer, optimized at test time against CLIP or reconstruction losses, performs image editing, inpainting, and class-conditional generation without training a generative model.

  3. InterLCM: Low-Quality Images as Intermediate States of Latent Consistency Models for Effective Blind Face Restoration

    cs.CV 2025-02 conditional novelty 6.0 of 10

    InterLCM restores low-quality faces by feeding them into a latent consistency model as an intermediate step, combining visual and spatial guidance to beat prior restoration methods with faster inference.

Pith tools