Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Flux 2 Klein 4B param, dropped at 2 steps with much higher FPS! I also added a couple of LORA's, I'll mess around with. Such a good diffusion model!

developedbyed's profile picture

Dev Ed

71,242 subscribers

109,619 Aufrufe • vor 6 Monaten •via X (Twitter)

Wissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

🆕 Image super-resolution model just dropped! Superior results even with a single sampling step. 🔥InvSR: Arbitrary-steps Image Super-resolution via Diffusion Inversion.
0:12

🆕 Image super-resolution model just dropped! Superior results even with a single sampling step. 🔥InvSR: Arbitrary-steps Image Super-resolution via Diffusion Inversion.

Gradio

53,331 Aufrufe • vor 1 Jahr

CharacterSheet LoRA by Alisson Pereira just dropped on HF and is so good 🎨 feed it one image of a character, photo or illustration, and this FLUX.2-klein LoRA generates a full model sheet: portrait, front, side and back, identity intact ▶️ on Spaces
0:15

CharacterSheet LoRA by Alisson Pereira just dropped on HF and is so good 🎨 feed it one image of a character, photo or illustration, and this FLUX.2-klein LoRA generates a full model sheet: portrait, front, side and back, identity intact ▶️ on Spaces

Hugging Apps

15,952 Aufrufe • vor 24 Tagen

🎨 We're open sourcing 4 new LoRAs trained with new fal FLUX.2 [klein] 4B Trainer! 🖼️ Outpaint - Expand your images beyond borders 🔍 Zoom - Select an area and regenerate it enlarged 🧹 Object Remove - Clean removal of unwanted objects 🎭 Background Remove - Seamless background extraction Model weights are on Hugging Face
0:10

🎨 We're open sourcing 4 new LoRAs trained with new fal FLUX.2 [klein] 4B Trainer! 🖼️ Outpaint - Expand your images beyond borders 🔍 Zoom - Select an area and regenerate it enlarged 🧹 Object Remove - Clean removal of unwanted objects 🎭 Background Remove - Seamless background extraction Model weights are on Hugging Face

fal

29,004 Aufrufe • vor 7 Monaten

Microsoft Asia just dropped Mage-Flow on Hugging Face a smol 4B model for image generation and editing that matches much larger models in quality and it's fast! 4 steps in < 1s at 1024x1024 (model goes up to 4K) try out on spaces
0:16

Microsoft Asia just dropped Mage-Flow on Hugging Face a smol 4B model for image generation and editing that matches much larger models in quality and it's fast! 4 steps in < 1s at 1024x1024 (model goes up to 4K) try out on spaces

Hugging Apps

48,339 Aufrufe • vor 1 Monat

I might've had WAY too much fun with oatmeal and a real mess afterwards... Such bulk... 🫠
0:15

Sensitive content

I might've had WAY too much fun with oatmeal and a real mess afterwards... Such bulk... 🫠

Kai!

36,969 Aufrufe • vor 3 Jahren

The usual suspect threatens customers at a Naples bar with scissors and gets a good dose of education. In Naples, you don't mess around.
0:17

The usual suspect threatens customers at a Naples bar with scissors and gets a good dose of education. In Naples, you don't mess around.

RadioGenoa

4,630,219 Aufrufe • vor 10 Monaten

Introducing Jan v3, with updates to Jan Desktop v0.7.6 💛 Jan v3 is our first v3 model, a 4B base built for fine-tuning and fast local use, with stronger math and coding. This release also includes a small Jan Desktop update, starting with a UI refresh as we move toward a more unified Jan experience. Try it: - Jan v3 is available in Jan Desktop and at - Get the latest desktop app at Model: - Jan-v3-4B: - Jan-v3-4B-GGUF: Thanks Qwen for the base model and Georgi Gerganov for llama.cpp 💛
0:17

Introducing Jan v3, with updates to Jan Desktop v0.7.6 💛 Jan v3 is our first v3 model, a 4B base built for fine-tuning and fast local use, with stronger math and coding. This release also includes a small Jan Desktop update, starting with a UI refresh as we move toward a more unified Jan experience. Try it: - Jan v3 is available in Jan Desktop and at - Get the latest desktop app at Model: - Jan-v3-4B: - Jan-v3-4B-GGUF: Thanks Qwen for the base model and Georgi Gerganov for llama.cpp 💛

👋 Jan

53,900 Aufrufe • vor 7 Monaten

Text-to-image diffusion transformer models learn to align text and image representations as a byproduct of their conditional denoising task. By taking the dot product between the text and image representations of a DiT model (like Flux 2), you can create rich saliency maps.
0:19

Text-to-image diffusion transformer models learn to align text and image representations as a byproduct of their conditional denoising task. By taking the dot product between the text and image representations of a DiT model (like Flux 2), you can create rich saliency maps.

Alec Helbling

94,195 Aufrufe • vor 8 Monaten

Last year when Krunal pandya tried to mess with MS Dhoni by bowling a bouncer ❌ MS Dhoni responded with 2 massive sixes of the next 2 balls 😮‍💨☠️ Never mess with MSD i repeat never ever 😎
0:20

Last year when Krunal pandya tried to mess with MS Dhoni by bowling a bouncer ❌ MS Dhoni responded with 2 massive sixes of the next 2 balls 😮‍💨☠️ Never mess with MSD i repeat never ever 😎

DB

152,894 Aufrufe • vor 5 Monaten

Along with Season 2 we added Impossibles to skate. Here’s a look at just a few of the ways you can do it!
0:14

Along with Season 2 we added Impossibles to skate. Here’s a look at just a few of the ways you can do it!

skate.

22,387 Aufrufe • vor 8 Monaten

Clarity Upscaler now works with Flux! 🥳 Clarity started 1 year ago as an upscaler to convert images with Stable Diffusion 1.5 into high-resolution, photorealistic images It took awhile to make it work with Flux but now it does. With Flux it's even better at upscaling faces while preserving identity and resemblance (a common problem with other upscalers) LoRAs are also supported, so upscaling with a specific style or face works perfectly Now available on Clarity AI and through my own API Link in the reply!
0:15

Clarity Upscaler now works with Flux! 🥳 Clarity started 1 year ago as an upscaler to convert images with Stable Diffusion 1.5 into high-resolution, photorealistic images It took awhile to make it work with Flux but now it does. With Flux it's even better at upscaling faces while preserving identity and resemblance (a common problem with other upscalers) LoRAs are also supported, so upscaling with a specific style or face works perfectly Now available on Clarity AI and through my own API Link in the reply!

philz1337x

71,216 Aufrufe • vor 1 Jahr

🐟🐠NEW MODEL REVEAL!!! 🐠🐟 As we set sail for the SEA-son 2, I would much rather show the process than hype up an invisible model for you to see at Season 2! Meet the your long forgotten imaginary friend once again with a new look. With a new raggedy/toylike feel 🧸
0:11

🐟🐠NEW MODEL REVEAL!!! 🐠🐟 As we set sail for the SEA-son 2, I would much rather show the process than hype up an invisible model for you to see at Season 2! Meet the your long forgotten imaginary friend once again with a new look. With a new raggedy/toylike feel 🧸

AlpineShowTime ⭐ Imaginary Friend VTuber ⭐

83,546 Aufrufe • vor 8 Monaten

2:30 am and I just started a movie with a 9 am class in a couple hours
0:14

2:30 am and I just started a movie with a 9 am class in a couple hours

💡

7,420,452 Aufrufe • vor 7 Monaten

i dont think i'll ever get over the way sasuke looked at naruto for such a long time with such an intense yearning expression
0:19

i dont think i'll ever get over the way sasuke looked at naruto for such a long time with such an intense yearning expression

🔆🌙

5,525,353 Aufrufe • vor 1 Jahr

One of my favorite days of camp with the Packers. Davante Adams, Funchess, Lazard. 3 different types of throws needed for higher probability of completion. I was obsessed with mastering fade types. I also knew I couldn’t give Jaire a chance to get his head around.
0:13

One of my favorite days of camp with the Packers. Davante Adams, Funchess, Lazard. 3 different types of throws needed for higher probability of completion. I was obsessed with mastering fade types. I also knew I couldn’t give Jaire a chance to get his head around.

Kurt Benkert

444,533 Aufrufe • vor 1 Jahr

First few tests with Seed Audio 1.0 from ByteDance and I'm loving it. In initial tests voice acting and foley seems much better than native audio from SeeDance 2. Also very cheap to experiment with. A 15 second audio test was only a couple of cents. Definitely something I could integrate into my workflow.
0:15

First few tests with Seed Audio 1.0 from ByteDance and I'm loving it. In initial tests voice acting and foley seems much better than native audio from SeeDance 2. Also very cheap to experiment with. A 15 second audio test was only a couple of cents. Definitely something I could integrate into my workflow.

TomLikesRobots🤖

38,990 Aufrufe • vor 2 Monaten

NVidia just released PiD: super resolution in pixel space directly from model latents 🔎 4X resolution for any generated image, FAST! 🏎️💨 FLUX.1, 2 and Z-Image (Qwen Image coming) of course, i built a demo: generate 4K images with Z-Image
0:12

NVidia just released PiD: super resolution in pixel space directly from model latents 🔎 4X resolution for any generated image, FAST! 🏎️💨 FLUX.1, 2 and Z-Image (Qwen Image coming) of course, i built a demo: generate 4K images with Z-Image

apolinario (poli)

29,948 Aufrufe • vor 3 Monaten

I do love .stl tricks basically making voids in the model forcing the slicer to generate walls to reinforce specific areas of a model also maxing out that Prusa3D Core one L bed space with 2 astromech parts
0:17

I do love .stl tricks basically making voids in the model forcing the slicer to generate walls to reinforce specific areas of a model also maxing out that Prusa3D Core one L bed space with 2 astromech parts

Nero3D the Canuck Creator

18,590 Aufrufe • vor 8 Monaten

I have playing with Black Forest Labs Black Forest Labs FLUX 3 for a few days now. (Thank you for the early access!) And I played with it... a lot. Some may say, too much. 😅 Here are some of my favorite gens. Needless to say, I love this model. Audio on! More in 🧵
0:20

I have playing with Black Forest Labs Black Forest Labs FLUX 3 for a few days now. (Thank you for the early access!) And I played with it... a lot. Some may say, too much. 😅 Here are some of my favorite gens. Needless to say, I love this model. Audio on! More in 🧵

Ostris

31,046 Aufrufe • vor 1 Monat