Crazy amount! Let's๐ค, so nothing breaks tomorrow hahah
El GTA VI paraliza las oficinas: Espaรฑa se sitรบa como el cuarto paรญs del mundo con mรกs solicitudes de dรญa libre para su estreno mrf.lu/2wQyg
4
106
๐๏ธ๐๏ธ๐๏ธ
P-Video-Upscale just got faster and cheaper! โก
Introducing Turbo mode: faster video upscaling at 65% lower cost compared to Standard (up to 30 fps), with a slight trade-off in quality.
Here's what you need to know:
- ๐ฃ๐ฟ๐ถ๐ฐ๐ถ๐ป๐ด: Starting at just $0.0035/s
- ๐ฆ๐ฝ๐ฒ๐ฒ๐ฑ: Faster processing across resolutions
- ๐ฅ๐ฒ๐๐ผ๐น๐๐๐ถ๐ผ๐ป: 720p, 1080p, 2K, or 4K
- ๐๐ฟ๐ฎ๐บ๐ฒ ๐ฟ๐ฎ๐๐ฒ: Up to 60 fps, at no extra cost in Turbo mode
Available via our inference partners @scenario_gg, @replicate, @WiroAI, @TellersAI, @eachlabs, @wavespeed_ai, Sociaro, and @runware.
๐ Model docs: docs.api.pruna.ai/guides/modโฆ
๐งฉ Try it through the API or Playground: dashboard.pruna.ai/login
P-Video-Upscale just got faster and cheaper! โก
Introducing Turbo mode: faster video upscaling at 65% lower cost compared to Standard (up to 30 fps), with a slight trade-off in quality.
Here's what you need to know:
- ๐ฃ๐ฟ๐ถ๐ฐ๐ถ๐ป๐ด: Starting at just $0.0035/s
- ๐ฆ๐ฝ๐ฒ๐ฒ๐ฑ: Faster processing across resolutions
- ๐ฅ๐ฒ๐๐ผ๐น๐๐๐ถ๐ผ๐ป: 720p, 1080p, 2K, or 4K
- ๐๐ฟ๐ฎ๐บ๐ฒ ๐ฟ๐ฎ๐๐ฒ: Up to 60 fps, at no extra cost in Turbo mode
Available via our inference partners @scenario_gg, @replicate, @WiroAI, @TellersAI, @eachlabs, @wavespeed_ai, Sociaro, and @runware.
๐ Model docs: docs.api.pruna.ai/guides/modโฆ
๐งฉ Try it through the API or Playground: dashboard.pruna.ai/login
Today, we open-source P-Q-Image-2.1-Remove-Object, 3 LoRA adapters for Qwen-Image-2.1 by @Alibaba_Qwen. Remove the object you point at, along with its shadow or reflection, and change nothing else!
- ๐๐ผ๐ ๐ฒ๐ณ๐ณ๐ถ๐ฐ๐ถ๐ฒ๐ป๐ ๐ถ๐ ๐ถ๐? Remove objects in 6 steps instead of 40, with no CFG. Use the 6-step adapter as the default. An 8-step adapter is also available, and a 40-step adapter runs only on the base model, without the few-step model's drift.
- ๐๐ผ๐ ๐ด๐ผ๐ผ๐ฑ ๐ถ๐ ๐ถ๐? Shadows and reflections just go away along with the object, even when they sit outside the outline. The rest of the photo stays put and lines up with the input, so you can use the result as is.
- ๐๐ผ๐ ๐ฑ๐ผ๐ฒ๐ ๐ถ๐ ๐๐ผ๐ฟ๐ธ? The adapters load directly on top of Qwen-Image-2.1, so the pipeline stays unchanged. The few-step variants stack on our P-Q-Image-2.1 distillation LoRA. Mark the object with a rough red outline, or just name it in the instruction.
๐ Blog: pruna.ai/blog/p-q-image-2.1-โฆ
๐ค Open Weights: huggingface.co/PrunaAI/P-Q-Iโฆ
โก๏ธ ComfyUI: huggingface.co/PrunaAI/P-Q-Iโฆ
Today, we open-source P-Q-Image-2.1-Remove-Object, 3 LoRA adapters for Qwen-Image-2.1 by @Alibaba_Qwen. Remove the object you point at, along with its shadow or reflection, and change nothing else!
- ๐๐ผ๐ ๐ฒ๐ณ๐ณ๐ถ๐ฐ๐ถ๐ฒ๐ป๐ ๐ถ๐ ๐ถ๐? Remove objects in 6 steps instead of 40, with no CFG. Use the 6-step adapter as the default. An 8-step adapter is also available, and a 40-step adapter runs only on the base model, without the few-step model's drift.
- ๐๐ผ๐ ๐ด๐ผ๐ผ๐ฑ ๐ถ๐ ๐ถ๐? Shadows and reflections just go away along with the object, even when they sit outside the outline. The rest of the photo stays put and lines up with the input, so you can use the result as is.
- ๐๐ผ๐ ๐ฑ๐ผ๐ฒ๐ ๐ถ๐ ๐๐ผ๐ฟ๐ธ? The adapters load directly on top of Qwen-Image-2.1, so the pipeline stays unchanged. The few-step variants stack on our P-Q-Image-2.1 distillation LoRA. Mark the object with a rough red outline, or just name it in the instruction.
๐ Blog: pruna.ai/blog/p-q-image-2.1-โฆ
๐ค Open Weights: huggingface.co/PrunaAI/P-Q-Iโฆ
โก๏ธ ComfyUI: huggingface.co/PrunaAI/P-Q-Iโฆ
Pruna v0.3.5 is out! ๐
Here are a few highlights:
- New FP8 quantization algorithms: static FP8, and time-aware FP8 for diffusion pipelines.
- New MSE metric in the evaluation toolbox
- Tighter security: safer checkpoint loading and a 7-day dependency cooldown
- New tutorials for FP8 quantization and sustainability benchmarking
๐ Read the notes: buff.ly/GnDidPi
Thank you all for your contribution!
New challenge to celebrate the P-Video-2-Pro Series! $2,000 Prize Pool!
๐ญ ๐๐๐๐ ๐๐๐ ๐๐๐๐. ๐๐๐๐๐ ๐๐๐ ๐๐๐๐๐.
๐ฃ-๐ฉ๐ถ๐ฑ๐ฒ๐ผ-๐ฎ-๐ฃ๐ฟ๐ผ ๐๐ฒ๐ฟ๐ถ๐ฒ๐. Generate the scene, lock the character, deliver the line, or recast the actor. Pick the model that fits the job.
Cut a vertical microdrama hook that proves quality, speed, or price.
Sara Han retweeted
Swap one or two people in a video using reference images while keeping the original motion, camera, framing, background, and audio intact.
@PrunaAI P-Video-2-Pro-Replace offers a practical way to explore different cast options without changing the scene.
Starting at $0.05 per second at 480p, with a 50% launch discount through November 19.
Introducing P-Video-2-Pro-Replace, based on @MiniMax_AI H3! ๐ฌ
Replace the people. Keep the scene.
Swap one or two people in an existing video using reference images, while preserving the original motion, camera, framing, background, and audio
And for launch, it's 50% off for the first two weeks, until November 19 at 6:00 PM CET!
Here's what you need to know:
- ๐ฃ๐ฟ๐ถ๐ฐ๐ถ๐ป๐ด: Starting from $0.05/s at 480p
- ๐ฆ๐ฝ๐ฒ๐ฒ๐ฑ: ~1.5โ2 minutes for a 10-second video
- ๐ฅ๐ฒ๐ณ๐ฒ๐ฟ๐ฒ๐ป๐ฐ๐ฒ๐: Replace up to two people using reference images
- ๐๐๐ฟ๐ฎ๐๐ถ๐ผ๐ป: Supports videos up to 120 seconds
Available via our inference partners @runware, @wavespeed_ai, Sociaro, @TellersAI, @WiroAI, @Segmind_ai, @replicate, and @eachlabs
๐ Model docs: docs.api.pruna.ai/guides/modโฆ
๐งฉ Try the model through the API or Playground: dashboard.pruna.ai/login
Sara Han retweeted
We created the P-video series with the fastest video models to replace characters, create avatars, or edit videos with any input.
Check them out on our playground: dashboard.pruna.ai/playgrounโฆ
Introducing P-Video-2-Pro-Replace, based on @MiniMax_AI H3! ๐ฌ
Replace the people. Keep the scene.
Swap one or two people in an existing video using reference images, while preserving the original motion, camera, framing, background, and audio
And for launch, it's 50% off for the first two weeks, until November 19 at 6:00 PM CET!
Here's what you need to know:
- ๐ฃ๐ฟ๐ถ๐ฐ๐ถ๐ป๐ด: Starting from $0.05/s at 480p
- ๐ฆ๐ฝ๐ฒ๐ฒ๐ฑ: ~1.5โ2 minutes for a 10-second video
- ๐ฅ๐ฒ๐ณ๐ฒ๐ฟ๐ฒ๐ป๐ฐ๐ฒ๐: Replace up to two people using reference images
- ๐๐๐ฟ๐ฎ๐๐ถ๐ผ๐ป: Supports videos up to 120 seconds
Available via our inference partners @runware, @wavespeed_ai, Sociaro, @TellersAI, @WiroAI, @Segmind_ai, @replicate, and @eachlabs
๐ Model docs: docs.api.pruna.ai/guides/modโฆ
๐งฉ Try the model through the API or Playground: dashboard.pruna.ai/login
Replying to @PrunaAI
@PrunaAI's P-Video-2-Pro-Replace is live on Runware on D0 ๐ฌ
Swap the people in a video you already have. Send a clip and one or two photos, and get the same video back with the new person: motion, camera and soundtrack kept, lips following the original audio.
- Source clips from 1 to 120s, mp4, mov or webm, any aspect ratio from 1:4 to 4:1
- One photo replaces one person, two photos replace two, matched left to right or by prompt
- 480p and 768p native, with 1080p, 2K and 4K upscaled from 768p
- Pruna reports ~10s of processing per second of video at 480p, ~12s at 768p
from $0.025 per second with 50% off until November 19 (regular from $0.05)
Introducing P-Video-2-Pro-Replace, based on @MiniMax_AI H3! ๐ฌ
Replace the people. Keep the scene.
Swap one or two people in an existing video using reference images, while preserving the original motion, camera, framing, background, and audio
And for launch, it's 50% off for the first two weeks, until November 19 at 6:00 PM CET!
Here's what you need to know:
- ๐ฃ๐ฟ๐ถ๐ฐ๐ถ๐ป๐ด: Starting from $0.05/s at 480p
- ๐ฆ๐ฝ๐ฒ๐ฒ๐ฑ: ~1.5โ2 minutes for a 10-second video
- ๐ฅ๐ฒ๐ณ๐ฒ๐ฟ๐ฒ๐ป๐ฐ๐ฒ๐: Replace up to two people using reference images
- ๐๐๐ฟ๐ฎ๐๐ถ๐ผ๐ป: Supports videos up to 120 seconds
Available via our inference partners @runware, @wavespeed_ai, Sociaro, @TellersAI, @WiroAI, @Segmind_ai, @replicate, and @eachlabs
๐ Model docs: docs.api.pruna.ai/guides/modโฆ
๐งฉ Try the model through the API or Playground: dashboard.pruna.ai/login
P-video-2-Pro-Replace is available now! Swap any character and create your own multiverse!
Introducing P-Video-2-Pro-Replace, based on @MiniMax_AI H3! ๐ฌ
Replace the people. Keep the scene.
Swap one or two people in an existing video using reference images, while preserving the original motion, camera, framing, background, and audio
And for launch, it's 50% off for the first two weeks, until November 19 at 6:00 PM CET!
Here's what you need to know:
- ๐ฃ๐ฟ๐ถ๐ฐ๐ถ๐ป๐ด: Starting from $0.05/s at 480p
- ๐ฆ๐ฝ๐ฒ๐ฒ๐ฑ: ~1.5โ2 minutes for a 10-second video
- ๐ฅ๐ฒ๐ณ๐ฒ๐ฟ๐ฒ๐ป๐ฐ๐ฒ๐: Replace up to two people using reference images
- ๐๐๐ฟ๐ฎ๐๐ถ๐ผ๐ป: Supports videos up to 120 seconds
Available via our inference partners @runware, @wavespeed_ai, Sociaro, @TellersAI, @WiroAI, @Segmind_ai, @replicate, and @eachlabs
๐ Model docs: docs.api.pruna.ai/guides/modโฆ
๐งฉ Try the model through the API or Playground: dashboard.pruna.ai/login
Introducing P-Video-2-Pro-Replace, based on @MiniMax_AI H3! ๐ฌ
Replace the people. Keep the scene.
Swap one or two people in an existing video using reference images, while preserving the original motion, camera, framing, background, and audio
And for launch, it's 50% off for the first two weeks, until November 19 at 6:00 PM CET!
Here's what you need to know:
- ๐ฃ๐ฟ๐ถ๐ฐ๐ถ๐ป๐ด: Starting from $0.05/s at 480p
- ๐ฆ๐ฝ๐ฒ๐ฒ๐ฑ: ~1.5โ2 minutes for a 10-second video
- ๐ฅ๐ฒ๐ณ๐ฒ๐ฟ๐ฒ๐ป๐ฐ๐ฒ๐: Replace up to two people using reference images
- ๐๐๐ฟ๐ฎ๐๐ถ๐ผ๐ป: Supports videos up to 120 seconds
Available via our inference partners @runware, @wavespeed_ai, Sociaro, @TellersAI, @WiroAI, @Segmind_ai, @replicate, and @eachlabs
๐ Model docs: docs.api.pruna.ai/guides/modโฆ
๐งฉ Try the model through the API or Playground: dashboard.pruna.ai/login
AI Toolkit now supports fine tuning P-H3-Image directly with a training adapter.
github.com/ostris/ai-toolkitโฆ
Today, we open-source P-H3-Image, an image generation and editing model built from MiniMax-H3 by @MiniMax_AI. A SOTA video model, turned into an efficient open image model.
- ๐๐ผ๐ ๐ฒ๐ณ๐ณ๐ถ๐ฐ๐ถ๐ฒ๐ป๐ ๐ถ๐ ๐ถ๐? Generate or edit images 5ร faster, in 8 steps instead of 50. A 4 MP image takes 2.6 s instead of 12.4 s. The model is 7ร smaller than H3, so high-resolution images are a light download and run on a much smaller GPU.
- ๐๐ผ๐ ๐ด๐ผ๐ผ๐ฑ ๐ถ๐ ๐ถ๐? Strongest at photorealism, documentary and editorial photography, film stills, and graphic styles with short quoted text. It renders 2 to 16 MP and edits with up to 8 input images.
-๐๐ผ๐ ๐ฑ๐ผ๐ฒ๐ ๐ถ๐ ๐๐ผ๐ฟ๐ธ? We reworked every component of H3: the prompt upsampler, the text encoder, the diffusion schedule, the transformer, and the decoder. Use it with Diffusers or ComfyUI.
๐ Tech Report: pruna.ai/blog/oss-p-h3-imageโฆ
๐ค @huggingface Open Weights: huggingface.co/PrunaAI/P-H3-โฆ
๐ @ComfyUI Native Support: huggingface.co/PrunaAI/P-H3-โฆ
Playing around with P-H3-Image, it's really cool!
Running on RTX3090
Using the lowest spec 4-bit (w4a8, with int8 VAE)
720p in about 50 seconds
1k in about 1 minute
Does solid text to image and image edits!
Today, we open-source P-H3-Image, an image generation and editing model built from MiniMax-H3 by @MiniMax_AI. A SOTA video model, turned into an efficient open image model.
- ๐๐ผ๐ ๐ฒ๐ณ๐ณ๐ถ๐ฐ๐ถ๐ฒ๐ป๐ ๐ถ๐ ๐ถ๐? Generate or edit images 5ร faster, in 8 steps instead of 50. A 4 MP image takes 2.6 s instead of 12.4 s. The model is 7ร smaller than H3, so high-resolution images are a light download and run on a much smaller GPU.
- ๐๐ผ๐ ๐ด๐ผ๐ผ๐ฑ ๐ถ๐ ๐ถ๐? Strongest at photorealism, documentary and editorial photography, film stills, and graphic styles with short quoted text. It renders 2 to 16 MP and edits with up to 8 input images.
-๐๐ผ๐ ๐ฑ๐ผ๐ฒ๐ ๐ถ๐ ๐๐ผ๐ฟ๐ธ? We reworked every component of H3: the prompt upsampler, the text encoder, the diffusion schedule, the transformer, and the decoder. Use it with Diffusers or ComfyUI.
๐ Tech Report: pruna.ai/blog/oss-p-h3-imageโฆ
๐ค @huggingface Open Weights: huggingface.co/PrunaAI/P-H3-โฆ
๐ @ComfyUI Native Support: huggingface.co/PrunaAI/P-H3-โฆ
Sara Han retweeted
Spent the last weeks doing model brain surgery on the MiniMax-H3 video model, turning it into a world-class image model. Everything is open, and we wrote a technical blog post about how we did it. Go read it.
pruna.ai/blog/oss-p-h3-imageโฆ
Sara Han retweeted
Pruna fine-tuned H3 to spit out a single frame, converting a video model back to an image model
and it does have a breath of fresh air in the aesthetics, I'm getting outputs out of this model that I can't get from other models
Today, we open-source P-H3-Image, an image generation and editing model built from MiniMax-H3 by @MiniMax_AI. A SOTA video model, turned into an efficient open image model.
- ๐๐ผ๐ ๐ฒ๐ณ๐ณ๐ถ๐ฐ๐ถ๐ฒ๐ป๐ ๐ถ๐ ๐ถ๐? Generate or edit images 5ร faster, in 8 steps instead of 50. A 4 MP image takes 2.6 s instead of 12.4 s. The model is 7ร smaller than H3, so high-resolution images are a light download and run on a much smaller GPU.
- ๐๐ผ๐ ๐ด๐ผ๐ผ๐ฑ ๐ถ๐ ๐ถ๐? Strongest at photorealism, documentary and editorial photography, film stills, and graphic styles with short quoted text. It renders 2 to 16 MP and edits with up to 8 input images.
-๐๐ผ๐ ๐ฑ๐ผ๐ฒ๐ ๐ถ๐ ๐๐ผ๐ฟ๐ธ? We reworked every component of H3: the prompt upsampler, the text encoder, the diffusion schedule, the transformer, and the decoder. Use it with Diffusers or ComfyUI.
๐ Tech Report: pruna.ai/blog/oss-p-h3-imageโฆ
๐ค @huggingface Open Weights: huggingface.co/PrunaAI/P-H3-โฆ
๐ @ComfyUI Native Support: huggingface.co/PrunaAI/P-H3-โฆ
Sara Han retweeted
We turned the SOTA H3 video model into an efficient open image model.
Read the blog here: pruna.ai/blog/oss-p-h3-imageโฆ
Today, we open-source P-H3-Image, an image generation and editing model built from MiniMax-H3 by @MiniMax_AI. A SOTA video model, turned into an efficient open image model.
- ๐๐ผ๐ ๐ฒ๐ณ๐ณ๐ถ๐ฐ๐ถ๐ฒ๐ป๐ ๐ถ๐ ๐ถ๐? Generate or edit images 5ร faster, in 8 steps instead of 50. A 4 MP image takes 2.6 s instead of 12.4 s. The model is 7ร smaller than H3, so high-resolution images are a light download and run on a much smaller GPU.
- ๐๐ผ๐ ๐ด๐ผ๐ผ๐ฑ ๐ถ๐ ๐ถ๐? Strongest at photorealism, documentary and editorial photography, film stills, and graphic styles with short quoted text. It renders 2 to 16 MP and edits with up to 8 input images.
-๐๐ผ๐ ๐ฑ๐ผ๐ฒ๐ ๐ถ๐ ๐๐ผ๐ฟ๐ธ? We reworked every component of H3: the prompt upsampler, the text encoder, the diffusion schedule, the transformer, and the decoder. Use it with Diffusers or ComfyUI.
๐ Tech Report: pruna.ai/blog/oss-p-h3-imageโฆ
๐ค @huggingface Open Weights: huggingface.co/PrunaAI/P-H3-โฆ
๐ @ComfyUI Native Support: huggingface.co/PrunaAI/P-H3-โฆ
Today, we open-source P-H3-Image, an image generation and editing model built from MiniMax-H3 by @MiniMax_AI. A SOTA video model, turned into an efficient open image model.
- ๐๐ผ๐ ๐ฒ๐ณ๐ณ๐ถ๐ฐ๐ถ๐ฒ๐ป๐ ๐ถ๐ ๐ถ๐? Generate or edit images 5ร faster, in 8 steps instead of 50. A 4 MP image takes 2.6 s instead of 12.4 s. The model is 7ร smaller than H3, so high-resolution images are a light download and run on a much smaller GPU.
- ๐๐ผ๐ ๐ด๐ผ๐ผ๐ฑ ๐ถ๐ ๐ถ๐? Strongest at photorealism, documentary and editorial photography, film stills, and graphic styles with short quoted text. It renders 2 to 16 MP and edits with up to 8 input images.
-๐๐ผ๐ ๐ฑ๐ผ๐ฒ๐ ๐ถ๐ ๐๐ผ๐ฟ๐ธ? We reworked every component of H3: the prompt upsampler, the text encoder, the diffusion schedule, the transformer, and the decoder. Use it with Diffusers or ComfyUI.
๐ Tech Report: pruna.ai/blog/oss-p-h3-imageโฆ
๐ค @huggingface Open Weights: huggingface.co/PrunaAI/P-H3-โฆ
๐ @ComfyUI Native Support: huggingface.co/PrunaAI/P-H3-โฆ



















