You're the one who started the game guys and act Like you don't know what the community want guys c'mon
https://redd.it/1pc5iux
@rStableDiffusion
https://redd.it/1pc5iux
@rStableDiffusion
Looking for best Lip sync AI
I'm working on a project where I need to match lip movements from one model in a video to different audio. I'm using wav2lip for a while now, and while it gets the job done, I'm curious what else is out there that might give better results.
I recently tried Lipsync video and was honestly impressed with the quality compared to wav2lip, cleaner syncing and less artifacting. But I'm the type who likes to have a few tools in rotation depending on the project.
What other AI lip sync tools have you used? Open to paid or free options. I just want to expand my toolkit a bit.
I'm interested in hearing about your experiences with different tools. What worked well for you? What didn't? I find that reviews from people using these tools are way more valuable than just reading feature lists on websites.
Thanks in advance for any recommendations or insights you can share.
https://redd.it/1pc9kto
@rStableDiffusion
I'm working on a project where I need to match lip movements from one model in a video to different audio. I'm using wav2lip for a while now, and while it gets the job done, I'm curious what else is out there that might give better results.
I recently tried Lipsync video and was honestly impressed with the quality compared to wav2lip, cleaner syncing and less artifacting. But I'm the type who likes to have a few tools in rotation depending on the project.
What other AI lip sync tools have you used? Open to paid or free options. I just want to expand my toolkit a bit.
I'm interested in hearing about your experiences with different tools. What worked well for you? What didn't? I find that reviews from people using these tools are way more valuable than just reading feature lists on websites.
Thanks in advance for any recommendations or insights you can share.
https://redd.it/1pc9kto
@rStableDiffusion
Reddit
From the StableDiffusion community on Reddit
Explore this post and more from the StableDiffusion community
Is CivArchive dying?
This is a great alternative to get loras that were deleted. For example, when Playtime_ai got banned (Prolific wan lora trainer), all his models would have been lost.
However I'm seeing no updates since Nov 24, and their discord invite is invalid, both bad signs.
With tensor *Having lots of its models deleted, it seems loras will continue getting harder to downlaod and share.
https://redd.it/1pcapqf
@rStableDiffusion
This is a great alternative to get loras that were deleted. For example, when Playtime_ai got banned (Prolific wan lora trainer), all his models would have been lost.
However I'm seeing no updates since Nov 24, and their discord invite is invalid, both bad signs.
With tensor *Having lots of its models deleted, it seems loras will continue getting harder to downlaod and share.
https://redd.it/1pcapqf
@rStableDiffusion
Reddit
From the StableDiffusion community on Reddit
Explore this post and more from the StableDiffusion community
Recreated a Gemini 3 comics page in Z-Image Turbo and Flux 2 dev !
In Gemeni 3 Pro (NB 2 Pro), I uploaded this Public Domain character and gave this prompt
https://preview.redd.it/v7zv3hnn4u4g1.jpg?width=624&format=pjpg&auto=webp&s=be3cde2286733c5af8f53c84374b73e2baf4de70
create a horror comics with this uploaded public domain character. She finds a door to a alternate dimension and enters into it. put proper dialogues. need 8 panels.
It gave me this one:
Nano Banana 2 Pro
It's good.
Then I asked Gemini to provide a full "text to image" prompt for reuse.
it gave this one:
An 8-panel sequential comic book page, vintage 1950s horror comics style, featuring a blonde female baseball player in a white uniform with a "B" cap (the public domain character "Babe"). Red and green color palette, thick ink outlines, heavy shadows, and Ben-Day dots for texture.
Panel 1: (Normal Reality) "Babe" at bat on a normal baseball field. Dialogue: "Just a practice swing."
Panel 2: (Discovery) "Babe" looking surprised at a mysterious, glowing, old wooden door standing alone in the outfield grass. Dialogue: "What the... A door? Here?"
Panel 3: (Investigation) Close-up of "Babe" reaching for the door, looking puzzled. Dialogue: "No lock... Where does it go?"
Panel 4: (Entry) "Babe" opening the door slightly, looking into darkness. Dialogue: "Hello? Anyone there?"
Panel 5: (Transition) "Babe" standing in a swirling vortex/portal of purple, black, and red. She is mid-step, looking panicked. Dialogue: "Whoa! What's happening?!"
Panel 6: (Alternate Dimension) A strange, surreal, alien baseball field. The ground is purple, the grass is bizarre fungi and glowing flora, with strange, menacing mushrooms surrounding the diamond. The field itself looks cracked and otherworldly. Dialogue: "This isn't the field..."
Panel 7: (Horror Reveal) A monstrous, horrifying, Cthulhu-esque creature bursts from the ground, covered in tentacles and dripping slime, roaring at "Babe." The background is a flash of intense red light. Dialogue: "GAAH! What is that?!"
Panel 8: (Action/Climax) "Babe" winds up to swing her baseball bat at the creature, eyes wide with determination and fear. She is framed against a violent red background, with motion lines around the bat. Onomatopoeia "CRACK!" is written near the impact point. Dialogue: "GET AWAY FROM ME!".
Then, I gave this one to Z-Image Turbo & Flux 2.
They nailed it.
Z-Image:
z-image
Flux 2 dev:
Flux 2
\--
I actually flabbergasted due to those outputs. Because NB 2 Pro is a closed source pipeline. So it produced a complex output.
But Z-Image & Flux 2 dev are open source single models. They able to create a comics.
Z-Image lags behind in text accuracy than Flux 2. But it will improve.
Also note that, since Gemini gave 'text desc' for the character uploaded, the other able to reproduce something near.
I for see a great promising future.
https://redd.it/1pcgqdm
@rStableDiffusion
In Gemeni 3 Pro (NB 2 Pro), I uploaded this Public Domain character and gave this prompt
https://preview.redd.it/v7zv3hnn4u4g1.jpg?width=624&format=pjpg&auto=webp&s=be3cde2286733c5af8f53c84374b73e2baf4de70
create a horror comics with this uploaded public domain character. She finds a door to a alternate dimension and enters into it. put proper dialogues. need 8 panels.
It gave me this one:
Nano Banana 2 Pro
It's good.
Then I asked Gemini to provide a full "text to image" prompt for reuse.
it gave this one:
An 8-panel sequential comic book page, vintage 1950s horror comics style, featuring a blonde female baseball player in a white uniform with a "B" cap (the public domain character "Babe"). Red and green color palette, thick ink outlines, heavy shadows, and Ben-Day dots for texture.
Panel 1: (Normal Reality) "Babe" at bat on a normal baseball field. Dialogue: "Just a practice swing."
Panel 2: (Discovery) "Babe" looking surprised at a mysterious, glowing, old wooden door standing alone in the outfield grass. Dialogue: "What the... A door? Here?"
Panel 3: (Investigation) Close-up of "Babe" reaching for the door, looking puzzled. Dialogue: "No lock... Where does it go?"
Panel 4: (Entry) "Babe" opening the door slightly, looking into darkness. Dialogue: "Hello? Anyone there?"
Panel 5: (Transition) "Babe" standing in a swirling vortex/portal of purple, black, and red. She is mid-step, looking panicked. Dialogue: "Whoa! What's happening?!"
Panel 6: (Alternate Dimension) A strange, surreal, alien baseball field. The ground is purple, the grass is bizarre fungi and glowing flora, with strange, menacing mushrooms surrounding the diamond. The field itself looks cracked and otherworldly. Dialogue: "This isn't the field..."
Panel 7: (Horror Reveal) A monstrous, horrifying, Cthulhu-esque creature bursts from the ground, covered in tentacles and dripping slime, roaring at "Babe." The background is a flash of intense red light. Dialogue: "GAAH! What is that?!"
Panel 8: (Action/Climax) "Babe" winds up to swing her baseball bat at the creature, eyes wide with determination and fear. She is framed against a violent red background, with motion lines around the bat. Onomatopoeia "CRACK!" is written near the impact point. Dialogue: "GET AWAY FROM ME!".
Then, I gave this one to Z-Image Turbo & Flux 2.
They nailed it.
Z-Image:
z-image
Flux 2 dev:
Flux 2
\--
I actually flabbergasted due to those outputs. Because NB 2 Pro is a closed source pipeline. So it produced a complex output.
But Z-Image & Flux 2 dev are open source single models. They able to create a comics.
Z-Image lags behind in text accuracy than Flux 2. But it will improve.
Also note that, since Gemini gave 'text desc' for the character uploaded, the other able to reproduce something near.
I for see a great promising future.
https://redd.it/1pcgqdm
@rStableDiffusion