🧨 Diffusers welcomes Stable Diffusion 3.5 Large
•
43
Apolinário from multimodal AI art PRO
multimodalart
AI & ML interests
None yet
Articles
Organizations
Posts
5
Post
16106
New feature 🔥
Image models and LoRAs now have little previews 🤏
If you don't know where to start to find them, I invite you to browse cool LoRAs in the profile of some amazing fine-tuners: @artificialguybr , @alvdansen , @DoctorDiffusion , @e-n-v-y , @KappaNeuro @ostris
Image models and LoRAs now have little previews 🤏
If you don't know where to start to find them, I invite you to browse cool LoRAs in the profile of some amazing fine-tuners: @artificialguybr , @alvdansen , @DoctorDiffusion , @e-n-v-y , @KappaNeuro @ostris
Post
21496
The first open Stable Diffusion 3-like architecture model is JUST out 💣 - but it is not SD3! 🤔
It is Tencent-Hunyuan/HunyuanDiT by Tencent, a 1.5B parameter DiT (diffusion transformer) text-to-image model 🖼️✨, trained with multi-lingual CLIP + multi-lingual T5 text-encoders for english 🤝 chinese understanding
Try it out by yourself here ▶️ https://huggingface.co/spaces/multimodalart/HunyuanDiT
(a bit too slow as the model is chunky and the research code isn't super optimized for inference speed yet)
In the paper they claim to be SOTA open source based on human preference evaluation!
It is Tencent-Hunyuan/HunyuanDiT by Tencent, a 1.5B parameter DiT (diffusion transformer) text-to-image model 🖼️✨, trained with multi-lingual CLIP + multi-lingual T5 text-encoders for english 🤝 chinese understanding
Try it out by yourself here ▶️ https://huggingface.co/spaces/multimodalart/HunyuanDiT
(a bit too slow as the model is chunky and the research code isn't super optimized for inference speed yet)
In the paper they claim to be SOTA open source based on human preference evaluation!
Collections
7
spaces
91
pinned
Running
on
Zero
416
🧪
FLUX LoRa Lab
pinned
Runtime error
1.22k
🏆
FLUX LoRa the Explorer
pinned
Running
on
Zero
716
👨🎤
Face to All
AI filter for your portraits
pinned
Running
on
Zero
367
🧞
LoRA Ease
Train LoRAs with Ease
Running
on
L40S
6
📈
Logo In Context
Add a logo to anything
Running
on
Zero
120
🖼
Kolors IP-Adapter
models
160
multimodalart/FLUX.1-dev2pro-full
Text-to-Image
•
Updated
•
11
multimodalart/product-design
Text-to-Image
•
Updated
•
2.83k
•
•
29
multimodalart/apolinario-steps
Text-to-Image
•
Updated
•
39
•
multimodalart/eery-liminal-space
Text-to-Image
•
Updated
•
363
•
•
9
multimodalart/liminal-spaces
Text-to-Image
•
Updated
•
15
•
multimodalart/tarsila-captioned
Text-to-Image
•
Updated
•
56
•
•
1
multimodalart/Florence-2-large-no-flash-attn
Image-Text-to-Text
•
Updated
•
56.2k
•
8
multimodalart/cat-toy-flux
Text-to-Image
•
Updated
•
205
•
•
4
multimodalart/plstps-local-feature
Text-to-Image
•
Updated
•
10.1k
•
•
2
multimodalart/vintage-ads-flux
Text-to-Image
•
Updated
•
5.79k
•
•
75
datasets
18
multimodalart/test-audio-dataset
Viewer
•
Updated
•
1
•
39
multimodalart/vintage-ads
Viewer
•
Updated
•
17
•
71
•
7
multimodalart/1920-raider-waite-tarot-public-domain
Viewer
•
Updated
•
78
•
118
•
41
multimodalart/steamboat-willy-frames
Updated
•
326
•
15
multimodalart/panda-70m
Viewer
•
Updated
•
804k
•
73
•
5
multimodalart/genai-book-images
Viewer
•
Updated
•
6
•
84
multimodalart/lora-fusing-preferences
Viewer
•
Updated
•
1.55k
•
51.2k
•
8
multimodalart/lora-ease-helper
Updated
•
55
•
1
multimodalart/repro_2_image
Viewer
•
Updated
•
2
•
24
multimodalart/repro_1_image
Viewer
•
Updated
•
1
•
14