Help Center

Models

Bugfixes / Misc

Features

Token

Characters

veniceai

New Submission

Backlog

In Review

Planned

Up next

In Progress

Completed

Rejected

High Priority

Low Priority

New Model

Chat

History

Image

Support

Web Search

Backup / Sync

Staking Contract

Voice

Points

Settings

Code

Folders

Payment

Video

UI Design

Stickers

Merchandise

Censorship

Context Window

Social

Enhance Prompt

Plugin

File Upload

Upscale/Enhance

Edit Prompt

Language

Privacy

Venice Pro

System Prompts

Vision

LoRAs

Image Editing

Memory

Social Feed

Artifacts

Auto Mode

Blog

Incentive Fund

Agents

Model Deprecation

Credits

Library

Projects

Marketing

Here’s what Venice is working on next!

Next up

Roadmap

All completed and shipped community requested feature requests and improvements can be seen here.

Done

Shipped Features

Hey {name|there}! 👋

I think that Qwen 2.5 VL is not smart enough to recognize images or describe them correctly. From my perspective, it would be nice if Llama 3.1 or Deepseek were the ones to recognize images.

Ich denke, dass Qwen 2.5 VL nicht intelligent genug ist, um Bilder zu erkennen oder sie richtig zu beschreiben. Aus meiner Sicht wäre es schön, wenn Llama 3.1 oder Deepseek die Bilder erkennen würden.

Bildscan für alle Modelle

Creo que Qwen 2.5 VL no es lo suficientemente inteligente como para reconocer imágenes o describirlas correctamente. Desde mi punto de vista, estaría bien que Llama 3.1 o Deepseek fueran los que reconocieran las imágenes. Cuidado con las imágenes.

Escaneado de imágenes para todos los modelos

Je pense que Qwen 2.5 VL n'est pas assez intelligent pour reconnaître les images ou les décrire correctement. De mon point de vue, il serait bien que ce soit Llama 3.1 ou Deepseek qui reconnaissent les images.

Analyse d'image pour tous les modèles

Image scan for all models

Venice.ai

Image scan for all models

Subscribe to post

Subscribe to post