Sylvain Filoni
fffiloni
AI & ML interests
ML for Animation • Alumni Arts Déco Paris
Articles
Organizations
fffiloni's activity
posted
an
update
2 months ago
Post
"The principle of explainability of ai and its application in organizations"
Louis Vuarin, Véronique Steyer
—› 📔 https://doi.org/10.3917/res.240.0179
ABSTRACT: The explainability of Artificial Intelligence (AI) is cited in the literature as a pillar of AI ethics, yet few studies explore its organizational reality. This study proposes to remedy this shortcoming, based on interviews with actors in charge of designing and implementing AI in 17 organizations. Our results highlight: the massive substitution of explainability by the emphasis on performance indicators; the substitution of the requirement of understanding by a requirement of accountability; and the ambiguous place of industry experts within design processes, where they are employed to validate the apparent coherence of ‘black-box’ algorithms rather than to open and understand them. In organizational practice, explainability thus appears sufficiently undefined to reconcile contradictory injunctions. Comparing prescriptions in the literature and practices in the field, we discuss the risk of crystallizing these organizational issues via the standardization of management tools used as part of (or instead of) AI explainability.
Vuarin, Louis, et Véronique Steyer. « Le principe d’explicabilité de l’IA et son application dans les organisations », Réseaux, vol. 240, no. 4, 2023, pp. 179-210.
#ArtificialIntelligence #AIEthics #Explainability #Accountability
Louis Vuarin, Véronique Steyer
—› 📔 https://doi.org/10.3917/res.240.0179
ABSTRACT: The explainability of Artificial Intelligence (AI) is cited in the literature as a pillar of AI ethics, yet few studies explore its organizational reality. This study proposes to remedy this shortcoming, based on interviews with actors in charge of designing and implementing AI in 17 organizations. Our results highlight: the massive substitution of explainability by the emphasis on performance indicators; the substitution of the requirement of understanding by a requirement of accountability; and the ambiguous place of industry experts within design processes, where they are employed to validate the apparent coherence of ‘black-box’ algorithms rather than to open and understand them. In organizational practice, explainability thus appears sufficiently undefined to reconcile contradictory injunctions. Comparing prescriptions in the literature and practices in the field, we discuss the risk of crystallizing these organizational issues via the standardization of management tools used as part of (or instead of) AI explainability.
Vuarin, Louis, et Véronique Steyer. « Le principe d’explicabilité de l’IA et son application dans les organisations », Réseaux, vol. 240, no. 4, 2023, pp. 179-210.
#ArtificialIntelligence #AIEthics #Explainability #Accountability
replied to
their
post
3 months ago
Nice 😊 Have you tried other models yet ? My favorite is Mustango so far, really good with NL prompts
posted
an
update
3 months ago
Post
I'm happy to announce that ✨ Image to Music v2 ✨ is ready for you to try and i hope you'll like it too ! 😌
This new version has been crafted with transparency in mind,
so you can understand the process of translating an image to a musical equivalent.
How does it works under the hood ? 🤔
First, we get a very literal caption from microsoft/kosmos-2-patch14-224; this caption is then given to a LLM Agent (currently HuggingFaceH4/zephyr-7b-beta )which task is to translate the image caption to a musical and inspirational prompt for the next step.
Once we got a nice musical text from the LLM, we can send it to the text-to-music model of your choice:
MAGNet, MusicGen, AudioLDM-2, Riffusion or Mustango
Instead of the previous version of Image to Music which used Mubert API, and could output curious and obscure combinations, we only provide open sourced models available on the hub, called via the gradio API.
Also i guess the music result should be more accurate to the atmosphere of the image input, thanks to the LLM Agent step.
Pro tip, you can adjust the inspirational prompt to match your expectations, according to the chosen model and specific behavior of each one 👌
Try it, explore different models and tell me which one is your favorite 🤗
—› fffiloni/image-to-music-v2
This new version has been crafted with transparency in mind,
so you can understand the process of translating an image to a musical equivalent.
How does it works under the hood ? 🤔
First, we get a very literal caption from microsoft/kosmos-2-patch14-224; this caption is then given to a LLM Agent (currently HuggingFaceH4/zephyr-7b-beta )which task is to translate the image caption to a musical and inspirational prompt for the next step.
Once we got a nice musical text from the LLM, we can send it to the text-to-music model of your choice:
MAGNet, MusicGen, AudioLDM-2, Riffusion or Mustango
Instead of the previous version of Image to Music which used Mubert API, and could output curious and obscure combinations, we only provide open sourced models available on the hub, called via the gradio API.
Also i guess the music result should be more accurate to the atmosphere of the image input, thanks to the LLM Agent step.
Pro tip, you can adjust the inspirational prompt to match your expectations, according to the chosen model and specific behavior of each one 👌
Try it, explore different models and tell me which one is your favorite 🤗
—› fffiloni/image-to-music-v2
- 8 replies
posted
an
update
3 months ago
Post
InstantID-2V is out ! ✨
It's like InstantID, but you get a video instead. Nothing crazy here, it's simply a shortcut between two demos.
Let's see how it does work with gradio API:
1. We call InstantX/InstantID with a conditional pose from cinematic camera shot (example provided in the demo)
2. Then we send the previous generated image to ali-vilab/i2vgen-xl
Et voilà 🤗 Try it : fffiloni/InstantID-2V
—
Note that generation can be quite long, so take the opportunity to brew you some coffee 😌
If you want to skip the queue, you can of course reproduce this pipeline manually
It's like InstantID, but you get a video instead. Nothing crazy here, it's simply a shortcut between two demos.
Let's see how it does work with gradio API:
1. We call InstantX/InstantID with a conditional pose from cinematic camera shot (example provided in the demo)
2. Then we send the previous generated image to ali-vilab/i2vgen-xl
Et voilà 🤗 Try it : fffiloni/InstantID-2V
—
Note that generation can be quite long, so take the opportunity to brew you some coffee 😌
If you want to skip the queue, you can of course reproduce this pipeline manually
- 1 reply
replied to
their
post
3 months ago
There is no DM here ☺️, everything is open and transparent, you can expose your idea, i’ll make my best to light the way 🤗
posted
an
update
3 months ago
Post
Quick build of the day: LCM Supa Fast Image Variation
—
We take the opportunity to combine moondream1 vision and LCM SDXL fast abilities to generate a variation from the subject of the image input.
All that thanks to gradio APIs 🤗
Try the space: https://huggingface.co/spaces/fffiloni/lcm-img-variations
—
We take the opportunity to combine moondream1 vision and LCM SDXL fast abilities to generate a variation from the subject of the image input.
All that thanks to gradio APIs 🤗
Try the space: https://huggingface.co/spaces/fffiloni/lcm-img-variations
-
-
- 3 replies
Sounds very promising !
replied to
their
post
4 months ago
Thanks for them @victor you should take a tour at the Open Days ;)
posted
an
update
4 months ago
Post
Just published a quick community blog post mainly aimed at Art and Design students, but which is also an attempt to nudge AI researchers who would like to better consider benefits from collaboration with designers and artists 😉
Feel free to share your thoughts !
"Breaking Barriers: The Critical Role of Art and Design in Advancing AI Capabilities" 📄 https://huggingface.co/blog/fffiloni/the-critical-role-of-art-and-design-in-advancing-a
—
This short publication follows the results of two AI Workshops that took place at École des Arts Décoratifs - Paris, lead by Etienne Mineur, Vadim Bernard, Martin de Bie, Antoine Pintout & Sylvain Filoni.
Feel free to share your thoughts !
"Breaking Barriers: The Critical Role of Art and Design in Advancing AI Capabilities" 📄 https://huggingface.co/blog/fffiloni/the-critical-role-of-art-and-design-in-advancing-a
—
This short publication follows the results of two AI Workshops that took place at École des Arts Décoratifs - Paris, lead by Etienne Mineur, Vadim Bernard, Martin de Bie, Antoine Pintout & Sylvain Filoni.
-
-
- 3 replies
posted
an
update
4 months ago
Post
I just published a Gradio demo for AliBaba's DreamTalk 🤗
Try it now: fffiloni/dreamtalk
Paper: DreamTalk: When Expressive Talking Head Generation Meets Diffusion Probabilistic Models (2312.09767)
—
DreamTalk is a diffusion-based audio-driven expressive talking head generation framework that can produce high-quality talking head videos across diverse speaking styles. DreamTalk exhibits robust performance with a diverse array of inputs, including songs, speech in multiple languages, noisy audio, and out-of-domain portraits.
Try it now: fffiloni/dreamtalk
Paper: DreamTalk: When Expressive Talking Head Generation Meets Diffusion Probabilistic Models (2312.09767)
—
DreamTalk is a diffusion-based audio-driven expressive talking head generation framework that can produce high-quality talking head videos across diverse speaking styles. DreamTalk exhibits robust performance with a diverse array of inputs, including songs, speech in multiple languages, noisy audio, and out-of-domain portraits.
