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
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
Simon Langrieger 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
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
Introducing P-Video-Upscale! ๐ฌ
Fast video upscaling to 720p, 1080p, 2K, or 4K, while preserving the original aspect ratio and audio. Need smoother motion? Increase the frame rate to up to 60 fps.
And for launch, it's 50% off for the first two weeks, until November 12 at 18:00 CET!
Here's what you need to know:
โข ๐ฃ๐ฟ๐ถ๐ฐ๐ถ๐ป๐ด: Starting from $0.01/s at 720p
โข ๐ฆ๐ฝ๐ฒ๐ฒ๐ฑ: ~1.7s per second of output video, depending on resolution
โข ๐๐ฟ๐ฎ๐บ๐ฒ ๐ฟ๐ฎ๐๐ฒ: Keep the original or interpolate up to 60 fps
โข ๐ง๐๐ฟ๐ฏ๐ผ ๐บ๐ผ๐ฑ๐ฒ: Faster processing with a slight quality trade-off
No need to regenerate a video just to get it in higher resolution.
Available via our inference partners @scenario_gg, @replicate, @WiroAI, @TellersAI, @eachlabs, @wavespeed_ai, Sociaro, and @runware.
Benchmarks by our benchmark partners @datapointai and @RapidataAI are coming soon.
๐ Model docs: docs.api.pruna.ai/guides/modโฆ
๐งฉ Try the model through the API or Playground: dashboard.pruna.ai/login
Today, we open-source v0.2 of P-Q-Image-2.1, two new 6-step LoRA adapters for Qwen-Image-2.1 by @Alibaba_Qwen. The first distillation that removes the prompt-upsampling step!
- ๐๐ผ๐ ๐ฒ๐ณ๐ณ๐ถ๐ฐ๐ถ๐ฒ๐ป๐ ๐ถ๐ ๐ถ๐? Generate or edit images in just 6 steps instead of 40. Use 6-steps for preserving inputs when editing and 6-steps-upsampled for improved visual quality and shorter end-to-end generation.
- ๐๐ผ๐ ๐ด๐ผ๐ผ๐ฑ ๐ถ๐ ๐ถ๐? 6-step distillation provides improved quality with few generation steps. 6-steps-upsampled is the first distillation that removes the need for a separate prompt-upsampling step. This means 41 to 80 seconds saved, depending on your prompt style.
- ๐๐ผ๐ ๐ฑ๐ผ๐ฒ๐ ๐ถ๐ ๐๐ผ๐ฟ๐ธ? The LoRA adapters load directly on top of Qwen-Image-2.1, so the pipeline stays unchanged. Few-step distillation cuts the diffusion cost, and the upsampled adapter also removes the prompt-upsampling step before image generation.
๐ค Open Weights: huggingface.co/PrunaAI/P-Q-Iโฆ
๐ HF Space: huggingface.co/spaces/PrunaAโฆ
Introducing P-Video-2-Pro-Avatar, based on @MiniMax_AI H3 !
Turn a single portrait into a realistic talking video with natural expressions and accurate lip sync.
And for launch, it's 50% off for the first two weeks, until November 5 at 18:00 CET!
โข ๐ฃ๐ฟ๐ถ๐ฐ๐ถ๐ป๐ด: $0.02/s at 480p ยท $0.04/s at 768p
โข ๐ฆ๐ฝ๐ฒ๐ฒ๐ฑ: ~0.97 s at 480p ยท ~2.2 s at 768p per second of output video
โข ๐๐ป๐ฝ๐๐: One portrait with a text script or uploaded audio
โข ๐ฉ๐ผ๐ถ๐ฐ๐ฒ๐: 30 voices across 10 languages
โข ๐๐๐ฟ๐ฎ๐๐ถ๐ผ๐ป: 1sโ3min at 24 fps, in 480p or 768p
โข ๐๐ผ๐ป๐๐ฟ๐ผ๐น: Voice delivery, scene motion, seed, and prompt upsampling
One image, two ways to bring it to life. Use your own audio or generate speech directly from text.
Available via our inference partners @replicate, @eachlabs, @Cloudflare, @scenario_gg, @wavespeed_ai, @WiroAI, Sociaro, @TellersAI, and @togethercompute.
๐ Model docs: docs.api.pruna.ai/guides/modโฆ
๐งฉ Try the model through the API or Playground: dashboard.pruna.ai/login
Simon Langrieger retweeted
p-video-2-pro is now the undisputed king of video models on @DesignArena.
#1 ELO, Only model on Pareto plots
it's just fun playing around with it! Iterating with it goes so fast, insane! Everything with a *single* prompt and a few references ๐ซช
greetings from eisbachwelle in munich ๐ค
Introducing P-Video-2-Pro-Reference based on @MiniMax_AI H3! ๐ฌ
Combine images, videos, and audio references to guide how your video looks, moves, and sounds. Keep characters consistent, transfer motion, and bring different visual elements together in a single generation.
โข ๐๐ป๐ฝ๐๐: Text prompt with image and/or video references, plus optional audio
โข ๐ฅ๐ฒ๐ณ๐ฒ๐ฟ๐ฒ๐ป๐ฐ๐ฒ๐: Up to 9 images, 3 videos, and 3 audio files
โข ๐๐๐ฟ๐ฎ๐๐ถ๐ผ๐ป: 5โ15s at 480p or 768p
โข ๐ฃ๐ฟ๐ถ๐ฐ๐ถ๐ป๐ด: Output starting at $0.015/s in Cost mode, with reference inputs billed separately
โข ๐๐ผ๐ป๐๐ฟ๐ผ๐น: First and last frames, seed, aspect ratio, and prompt upsampling
Two modes: Speed and Cost. Choose the trade-off that fits your workflow.
Available via our inference partners @Cloudflare, @scenario_gg, @replicate, @WiroAI, @TellersAI, @eachlabs, @wavespeed_ai, @inference_sh, @_segmind, @togethercompute, @EdenAIco, and @runware
Validated by our benchmark partners @datapointai, @RapidataAI, and @DesignArena
๐ Model docs: docs.api.pruna.ai/guides/modโฆ
๐งฉ API: dashboard.pruna.ai/login
Simon Langrieger retweeted
P-video-2-pro slowly climbed up to #1 ELO model on quality! Not only that, it is also the fastest and cheapest model on the market.
There is literally 0 reason to use any other video model anymore.
Image-to-Video: P-Video-2-Pro is the #1 ELO model on @DesignArena.
โข Speed: #1 ยท 1328 Elo
โข Quality: #2 ยท 1326 Elo
โข Cost: #3 ยท 1324 Elo
One model, three modes. Depending on whether you want to optimize for cost, speed, or quality.
Benchmark by @DesignArena.
๐ Documentation: buff.ly/bHQHKV0
๐งฉ API: dashboard.pruna.ai
๐ฅ P-Bench: buff.ly/81e3AuS
P-Video-2-Pro now has a Cost mode!
Get the same output quality as Speed mode, now starting from just $0.01/s. Optimised for cost when generation time matters less.
And for launch, itโs 50% off until October 13!
โข ๐๐ป๐ฝ๐๐: Text or first-frame image, with optional last-frame conditioning
โข ๐๐๐ฟ๐ฎ๐๐ถ๐ผ๐ป: 5โ15s with generated audio
โข ๐ฃ๐ฟ๐ถ๐ฐ๐ถ๐ป๐ด: $0.01/s at 480p ยท $0.025/s at 768p
โข ๐๐ผ๐ป๐๐ฟ๐ผ๐น: First + last frame, seed, aspect ratio, and prompt upsampling
Three modes: Cost, Speed, Quality. Pick the tradeoff that fits your workflow.
Available via our inference partners @Cloudflare, @Scenario_gg, @replicate, @wiroai, @TellersAI, @eachlabs, @edenaico, @runware, @wavespeed_ai, @inference_sh, @togethercompute, and @prodialabs.
Validated by our benchmark partners @datapointai, @RapidataAI, and @DesignArena.
๐ Model docs: docs.api.pruna.ai/guides/modโฆ
๐งฉ API: dashboard.pruna.ai/login
P-Video-2-Pro dominates the quality-speed frontier on @DesignArena for both Text-to-Video and Image-to-Video!
Image-to-Video:
โข Quality: #3 ยท 1325 Elo ยท 8.0s
โข Speed: #2 ยท 1325 Elo ยท 4.5s
Text-to-Video:
โข Quality: #4 ยท 1308 Elo ยท 8.6s
โข Speed: #6 ยท 1298 Elo ยท 4.7s
Thatโs a 19โ22 place jump from P-Video-2.
Simon Langrieger retweeted
Shoutouts to our distillation wizard @simlang_. It was a lot of fun to build together, and I'm proud of how far we got in the limited time we had.
Today, we open-source Pruna-Qwen-Image-2.1, a set of a few-step LoRA adapters that make Qwen-Image-2.1 by @Alibaba_Qwen up to 6.3ร faster for image generation and editing.
- ๐๐ผ๐ ๐ฒ๐ณ๐ณ๐ถ๐ฐ๐ถ๐ฒ๐ป๐ ๐ถ๐ ๐ถ๐? Generate or edit images in just 5 or 8 steps instead of 40. Choose 5 steps for maximum speed or 8 steps for the best balance.
- ๐๐ผ๐ ๐ด๐ผ๐ผ๐ฑ ๐ถ๐ ๐ถ๐? The 8-step adapter is our recommended default. It supports text-to-image and single- or multi-image editing at 1K resolution, with up to three reference images.
- ๐๐ผ๐ ๐ฑ๐ผ๐ฒ๐ ๐ถ๐ ๐๐ผ๐ฟ๐ธ?The LoRA adapters load directly on top of Qwen-Image-2.1, while the pipeline remains unchanged. Each adapter uses its own optimized sigma schedule and runs without CFG.
๐๐ฉ๐ช๐ด ๐ช๐ด ๐ซ๐ถ๐ด๐ต ๐ฐ๐ถ๐ณ ๐ง๐ช๐ณ๐ด๐ต ๐ณ๐ฆ๐ญ๐ฆ๐ข๐ด๐ฆ, ๐ธ๐ช๐ต๐ฉ ๐ฆ๐ท๐ฆ๐ฏ ๐ฃ๐ฆ๐ต๐ต๐ฆ๐ณ ๐ท๐ฆ๐ณ๐ด๐ช๐ฐ๐ฏ๐ด ๐ฐ๐ฏ ๐ต๐ฉ๐ฆ ๐ธ๐ข๐บ. ๐
Want to try the fast open-source integration? Check it here on Diffusers: buff.ly/1CpiRPp
Want to try the fastest image generation and editing endpoint? Check P-Image-Ideogram and P-Image-Edit here on API: buff.ly/gw5tvUV
Simon Langrieger retweeted
In case you ever wondered how I got good at optimizing models... hereโs my story.
Made with P-Video-2-Pro for less than $2 and in under 2 minutes.
Simon Langrieger retweeted
P-Video-2-Pro by @PrunaAI built on MiniMax H3 ๐
Now on available on all our inference partners @replicate, @Cloudflare, @eachlabs, @scenario_gg, @TellersAI, @wavespeed_ai, @wiroai, @runware, @togethercompute.
๐ Docs: docs.api.pruna.ai/guides/modโฆ
๐งฉ API: dashboard.pruna.ai/login
There are already some very fast @MiniMax_AI H3 implementations out there, both open- and closed source.
But how much performance can you get per dollar?
Today @PrunaAI is launching P-Video-2-Pro, fast, affordable and built for high-quality video generation at scale
Today, we launch P-Video-2-Pro, based on MiniMax H3: The best quality. The best speed.
Text or image in. Video and audio out.
โข ๐๐ป๐ฝ๐๐: Text or first-frame image, with optional last-frame conditioning
โข ๐ฆ๐ฝ๐ฒ๐ฒ๐ฑ: ~2.0s for a 5s clip at 480p ยท ~4.3s at 768p in Speed mode
โข ๐ฃ๐ฟ๐ถ๐ฐ๐ถ๐ป๐ด: From $0.02/s Speed ยท $0.04/s Quality
โข ๐ ๐ผ๐ฑ๐ฒ๐: Speed or Quality
โข ๐๐ผ๐ป๐๐ฟ๐ผ๐น: First and last frame, seed, aspect ratio, and prompt upsampling with Off, Turbo, or Max
Available via our inference partners @replicate, @Cloudflare, @eachlabs, @scenario_gg, @TellersAI, @wavespeed_ai, @wiroai, @runware, and @togethercompute
Validated by our benchmark partners @datapointai, @RapidataAI, and @DesignArena. Benchmarks to be released soon ๐
๐ Free Playground: playground.pruna.ai/
๐ Model docs: docs.api.pruna.ai/guides/modโฆ
๐งฉ API: dashboard.pruna.ai/login
P-Image-Ideogram, built with @ideogram_ai, now has a Very High mode.
Very High uses test-time scaling to push final image quality further. Built for hero assets, difficult prompts, and quality-critical generations when people and products have to pop.
โข ~5.55s at 1K ยท $0.033/image (1K) ยท $0.066/image (2K)
โข Five modes from Very Low ($0.003) through Very High
Again, benchmarks agree: This new very high mode is on efficiency-quality based on human and automated evals from @datapointai, @DesignArena, and P-Judger. Full benchmarks results follow in a later post on P-Bench.
Available on @cloudflare @ComfyUI @GammaApp @inference_sh @kittldesign @LeonardoAi @lovart_ai @magnific @picsart @replicate @runware @scenario_gg @togethercompute @wavespeed_ai @wiroai
๐ Free Playground: playground.pruna.ai/p-image-โฆ
๐งฉ API: docs.pruna.ai/
๐ Model page: pruna.ai/p-image-ideogram













