apolinario ๐
@multimodalart
Followers
15K
Following
6K
Media
993
Statuses
4K
ML for Art and Creativity, working @HuggingFace ([email protected])
Joined July 2021
๐ Hello, Kimi K2 Thinking! The Open-Source Thinking Agent Model is here. ๐น SOTA on HLE (44.9%) and BrowseComp (60.2%) ๐น Executes up to 200 โ 300 sequential tool calls without human interference ๐น Excels in reasoning, agentic search, and coding ๐น 256K context window Built
214
408
3K
Qwen Image Multiple Angles LoRA is an exquisitely trained LoRA! ๐หโโง๊ฐแ Keep character and scenes consistent, and flies the camera around! Open source got there! One of the best LoRAs I've come across lately ๐
49
203
2K
Talkspace online therapy is provided by deeply experienced human therapists using evidence-based methods proven to achieve positive results.
2
11
78
Qwen Image Multiple Angles LoRA is an exquisitely trained LoRA! ๐หโโง๊ฐแ Keep character and scenes consistent, and flies the camera around! Open source got there! One of the best LoRAs I've come across lately ๐
49
203
2K
This is more than just four quarters. Itโs every tailgate, every chant, every moment. Itโs fuel that goes beyond the field. This is CELSIUS! LIVE. FIT. GO.
253
422
8K
adding camera control to the list of things Qwen Image Edit is great at + with a specialized multi-angle LoRA it's even betterโจ > rotate the camera > tilt between birdโs-eye and wormโs-eye views > adjust lens (wide, close-up) of course we built a demo for it ๐ค๐น
14
86
662
Qwen-Edit 2509 Image Fusion LoRA. Product image composition; blends objects into new backgrounds; automatically attempts to correct perspective and harmonize lighting for seamless integration. https://t.co/5GvrPquRKK
8
61
778
this is so good! mid-frames are here, multi-frame to video is an easy to use workflow! kudos to @morphic for open sourcing it
Morphic's frames-to-video, with up to 5 frames and time control, is now open-source. GitHub: https://t.co/O15v89IaSr Hugging Face: https://t.co/yRDpUni69j More details in the thread:
3
42
314
Weights are out! ๐ฅ FIBO is a new open weights high quality 8B image model by @bria_ai_ trained on json prompts! It can generate and modify images with a precisely crafted json prompt, allowing for every detail of the image to be decided Try it here: https://t.co/16xNHUGQ8B
3
13
92
Insights from Condoleezza Rice, Victor Davis Hanson & more. Hoover's top minds tackle policy, security & the economy.
0
49
274
๐จIn our NeurIPS paper, we bring encoder-decoders back.. for diffusion language models! โก๏ธEncoder-decoders make diffusion sampling fast: a small (fast) decoder denoises tokens progressively and a large (slower) encoder represents clean context.
8
36
240
this is so good! mid-frames are here, multi-frame to video is an easy to use workflow! kudos to @morphic for open sourcing it
Morphic's frames-to-video, with up to 5 frames and time control, is now open-source. GitHub: https://t.co/O15v89IaSr Hugging Face: https://t.co/yRDpUni69j More details in the thread:
3
42
314
Morphic's frames-to-video, with up to 5 frames and time control, is now open-source. GitHub: https://t.co/O15v89IaSr Hugging Face: https://t.co/yRDpUni69j More details in the thread:
6
45
332
many folks have been trying json prompting with image and video models, bria trained the model to take that in natively! super cool model ๐
Weights are out! ๐ฅ FIBO is a new open weights high quality 8B image model by @bria_ai_ trained on json prompts! It can generate and modify images with a precisely crafted json prompt, allowing for every detail of the image to be decided Try it here: https://t.co/16xNHUGQ8B
0
2
23
Itโs basically a rule of life: teenagers get mad at their parents. But that doesnโt mean you canโt have a relationship with them. If you want to know how to build a connection with your kid (even if theyโre mad at you), read this:
323
480
5K
Weights are out! ๐ฅ FIBO is a new open weights high quality 8B image model by @bria_ai_ trained on json prompts! It can generate and modify images with a precisely crafted json prompt, allowing for every detail of the image to be decided Try it here: https://t.co/16xNHUGQ8B
3
13
92
A next-gen visual model trained on structured JSON for precise, controllable generation. ๐ช FIBO is a text-to-image model that transforms prompts into JSON schemas, enabling predictable visuals at scale. Trained on extended, structured captionsโoften 1,000+ wordsโFIBO
2
9
52
China's open source is just on fire. Soul, China's Tinder (?), has just open sourced their podcast model on @huggingface
https://t.co/laie6kUMqd
huggingface.co
16
49
511
Today, we are open-sourcing Hunyuan World 1.1 (WorldMirror), a universal feed-forward 3D reconstruction model. ๐๐๐ ย While our previously released Hunyuan World 1.0 (open-sourced, lite version deployable on consumer GPUs) focused on generating 3D worlds from text or
45
265
2K
Makeup that works as skincare. Use cosmetic creations crafted with pure plant pigments, essential minerals, and skin-loving lipids.
0
1
1
Great work scaling Self-Forcing up to 14B models, improving extrapolation, while still keeping it running in real time.
Krea Realtime is distilled from the Wan 2.1 14B text-to-video model using Self-Forcing. It achieves a text-to-video inference speed of 11fps using 4 inference steps on a single NVIDIA B200 GPU check all our training methodology and sampling innovations in our technical report!
1
5
112
today we're open-sourcing Krea Realtime. this 14B autoregressive model is 10x larger than any open-source equivalent, and it can generate long-form videos at 11 fps on a single B200. weights and technical report below ๐
58
204
1K