this post was submitted on 23 Sep 2024
10 points (100.0% liked)

Stable Diffusion

4309 readers
4 users here now

Discuss matters related to our favourite AI Art generation technology

Also see

Other communities

founded 1 year ago
MODERATORS
 

Qwen2-VL-7B-Captioner-Relaxed is an instruction-tuned version of Qwen2-VL-7B-Instruct, an advanced multimodal large language model. This fine-tuned version is based on a hand-curated dataset for text-to-image models, providing significantly more detailed descriptions of given images.

top 1 comments
sorted by: hot top controversial new old
[–] j4k3@lemmy.world 3 points 1 month ago* (last edited 1 month ago)

You using this in a toolchain? I haven't tried any of the Qwen models yet, or Yi for that matter. I tried at one point early on, but they were not working well with my stuff and I had no complaints with Mistral stuff. I like some underlying things with a MoE for speed and underlying entity/realm stuff I can access in my favorite.

I'm curious if anyone has constructive contextual feedback about what makes these unique or worth exploring.