Pleased to see another model has caught uphttps://t.co/G5UFg6eCMc
— fofr (@fofrAI) 20 juin 2025
Pleased to see another model has caught up
@fofrai
-
Another AI Model Reaches Competitive Performance Parity
By
–
-
Seedance 1 Lite Now Available on Replicate Platform
By
–
Seedance 1 Lite is now on Replicate.
— fofr (@fofrAI) 20 juin 2025
~$0.08 for 5s 480p
~$0.18 for 5s 720phttps://t.co/p4NdMOrhUZ
> a woman stops walking, drinks from the straw in her cup (once), she looks at the billboard, and then walks away, past the billboard, she is happy pic.twitter.com/OAMpSfzoXESeedance 1 Lite is now on Replicate. ~$0.08 for 5s 480p
~$0.18 for 5s 720p https://
replicate.com/bytedance/seed
ance-1-lite
… > a woman stops walking, drinks from the straw in her cup (once), she looks at the billboard, and then walks away, past the billboard, she is happy -
Real-time Generative Movies: Exciting Milestones Ahead
By
–
Now: 8s videos with audio in about 3 minutes
.
.
.
.
Future: real time generative movies, episodes, lectures; they generate as you watch them, with steerable mechanisms during viewing. They are captivating and worth watching. What are the exciting intermediate milestones? -
Kling v2.1 Master Handles Unusual Creative Prompts Well
By
–
Kling v2.1 Master does pretty well with some of my more unusual prompts https://t.co/efkoJLJdLY pic.twitter.com/q8byp6WWHl
— fofr (@fofrAI) 19 juin 2025Kling v2.1 Master does pretty well with some of my more unusual prompts
-
Join SF Hackathon: Kontext Development with BFL Team
By
–
Come join us in SF on Saturday to hack on Kontext with the BFL team
-
MJ Video Animates Text Better Than Expected
By
–
MJ video does better at animating text than I expected.
— fofr (@fofrAI) 19 juin 2025
Here's an ideogram v3 image with text overlaying a photo, then the prompt:
> animate the letters of the text pic.twitter.com/uEP9THk6DAMJ video does better at animating text than I expected. Here's an ideogram v3 image with text overlaying a photo, then the prompt: > animate the letters of the text
-
Reviving 2022 Midjourney Generations with Enhanced Capabilities
By
–
Bringing some life to old 2022 MJ gens https://t.co/ULVlrt2KKs pic.twitter.com/psbhcKfQDK
— fofr (@fofrAI) 19 juin 2025Bringing some life to old 2022 MJ gens
-
Native Audio Generation with Dialogue Surpasses MMAudio Quality
By
–
MMAudio is great, but native audio generation, especially with dialogue and expression, it hits differently.
-
First Native Audio Video Model After Veo 3
By
–
Who's going to be first to drop a video model with native audio after Veo 3?
-
Midjourney Video Model Outputs: Styles, Speed, and Coherence
By
–
A selection of outputs from Midjourney video. It's clearly not the most coherent or realistic of video models, but it's fun to create with – results are fast, you get 4 to compare, and it handles different styles really well. https://t.co/AB7mxNGXvy pic.twitter.com/suRnqxJp76
— fofr (@fofrAI) 18 juin 2025A selection of outputs from Midjourney video. It's clearly not the most coherent or realistic of video models, but it's fun to create with – results are fast, you get 4 to compare, and it handles different styles really well.