Florian Soudan

AI team lead, I manage cross functional teams delivering industrial AI solutions.

[Florian Soudan @FSoudan]

@mervenoyann Thanks. Have you shared somewhere your local coding setup (software and hardware)?

[Florian Soudan @FSoudan]

@RisingSayak @ben_nebulous Surprisingly Nano Banana 2 is doing quite well but love the work done to have physically correct. Ground work for world models!

[Florian Soudan @FSoudan]

@PontiEdoardo Very interesting! Isn’t the model way slower as the inputs and outputs are now 3 to 5 times longer?

[Florian Soudan @FSoudan]

@mervenoyann Thanks for that.
Generic question on your training notebooks: why you don’t use lightning or any PyTorch training lib? Is do you need specific control you would not get?

[Florian Soudan @FSoudan]

@Prince_Canuma Hey MLX Prince! I was wandering if you were planning to keep working on Phi 4? I tried transformer code and the ONNX version both on MPS with no luck. Thanks again for all the work you do for the community

[Florian Soudan @FSoudan]

@Prince_Canuma @lin72h @lllucas @ivanfioravanti @love_police_ok Hey! Thanks so much for your work! Do you plan to work on Phi 4 multimodal to finish it in a near future? 🙏🏻

[Florian Soudan @FSoudan]

@ClementDelangue @huggingface Me! 🤗

[Florian Soudan @FSoudan]

@fchollet Same here. Let us know where we can still follow you 🙏🏻

[Florian Soudan @FSoudan]

@_akhaliq @huggingface Do you post different content on HF?

[Florian Soudan @FSoudan]

@simonw We did extensive OCR tests and Gemini Flash 1.5 is amazing, you can disable any safety check in the arguments of the call. No open source model comes close to it

[Florian Soudan @FSoudan]

@Prince_Canuma Love the composition and design of B. I think it just lacks "Llama" for your usage

[Prince Canuma @Prince_Canuma]

LLaVA Llama-3 and Phi-3 now on MLX 🎉🚀

You can now run inference locally on your Mac.

pip install -U mlx-vlm

I’m getting ~50 tokens on a M3 Max.

Model cards 👇🏾

[Florian Soudan @FSoudan]

@Prince_Canuma @stablequan That’s great! Thanks. Next on your list should be Idefics 2, I got great results with it

[Florian Soudan @FSoudan]

@arpitingle Can we talk about the answer of the model? 😂

[Florian Soudan @FSoudan]

@julien_c Excellent, thanks 🤗 team! It works perfectly and Lama 3 70b is so fast!

[Florian Soudan @FSoudan]

@mervenoyann Amazing! Thanks @mervenoyann. You are now my reference at work « here a new post of Merve, let’s check that guys » 😅

[Florian Soudan @FSoudan]

@Lykon4072 Congrats! This result is amazing with very difficult features usually not well understood by diffusion models: a single contrastive color applied only on the proper spots and high contrast.
Question: do you get the texture directly out of #SD3 (no upscaler or refiner or post)?

[Florian Soudan @FSoudan]

@BenGeskin Ahah @Bouletcorp on a du te tagguer 100 fois sur cette vidéo 🤣

[Florian Soudan @FSoudan]

@Lykon4072 Thanks great work! The model looks amazing, can’t wait to get access to it

[Florian Soudan @FSoudan]

@Lykon4072 SD3 seems to be very "raw" compared to MJ6 which tends to force its aesthetic. How much have you worked on the style in the prompt to get this image? Or was it a lucky generation?