Search found 12 matches

Author Message

hempires

Post 12-Jun-2024 19:56

for those that haven't downloaded the entire repo (like myself), you can still seed just the weights :)

FullOf_Bad_Ideas

Post 12-Jun-2024 17:42

I put up an ungated mirror on HF and shared the link to this torrent
https://huggingface.co/adamo1139/stable-diffusion-3-medium-ungated

Nafumal

Post 12-Jun-2024 17:22

Anyone shared the link around? We've got good upload now

valCooL

Post 12-Jun-2024 16:21

87
85I did as Nafumal suggested. Will be seeding with 300mbps for a few hours at least, I think this will help.
Same, got it from HF and seeding from seedbox now.
you rock!

thefi3nd

Post 12-Jun-2024 16:14

85I did as Nafumal suggested. Will be seeding with 300mbps for a few hours at least, I think this will help.
Same, got it from HF and seeding from seedbox now.

valCooL

Post 12-Jun-2024 16:03

85I did as Nafumal suggested. Will be seeding with 300mbps for a few hours at least, I think this will help.
Thanks, mate!

FullOf_Bad_Ideas

Post 12-Jun-2024 16:00

I did as Nafumal suggested. Will be seeding with 300mbps for a few hours at least, I think this will help.

valCooL

Post 12-Jun-2024 15:48

Yeah guys, it would be super helpful to join the seed, as my uplink is kinda sweating right now.

FullOf_Bad_Ideas

Post 12-Jun-2024 15:41

good idea, i'll do that.

Nafumal

Post 12-Jun-2024 15:33

If you've already DL'd the og repo and want to seed you can download the torrent and point it to the folder the repo's folder is in (not the repo's folder itself) and "verify local data"

FullOf_Bad_Ideas

Post 12-Jun-2024 15:22

no seeders here.

valCooL

Post 12-Jun-2024 15:13

SD3 Medium is Here!
Key Takeaways:
• 2 Billion Parameters: Stability AI’s most advanced text-to-image model yet.
• Accessible: Perfect for consumer PCs, laptops, and enterprise GPUs.
• Open Licensing: Available under a non-commercial license and a low-cost Creator License. Contact us for large-scale commercial use.
Features:
• Photorealism: Overcomes common artifacts in hands and faces.
• Prompt Adherence: Handles complex prompts with spatial relationships and styles.
• Typography: Generates text without artifacts using Diffusion Transformer architecture.
• Resource-efficient: Runs on standard consumer GPUs with low VRAM footprint.
• Fine-Tuning: Customizable with small datasets.
Collaborations:
• NVIDIA: Enhanced performance with RTX GPUs and TensorRT for a 50% boost.(here)
• AMD: Optimized inference for various AMD devices.
Open and Accessible:
• Released under the Stability Non-Commercial Research Community License.
• Professional use encouraged with our Creator License. Contact us for commercial licensing. (TLDR generations are still free to use, commercial and donate-ware finetunes are paid now)
Safety:
• Committed to safe, responsible AI with extensive testing and safeguards. (read as lobotomized in the same way as SDXL was)
 

The current time is: 23-Jul 06:17

All times are UTC + 1

Cover our bill…

Donate at ko-fi.com

Or use crypto:

We accept BTC, XMR, LTC, BCH & DOGE