LenSch (@LennScha) header
LenSch (@LennScha) profile picture

Machine Learning Engineer @PrunaAI

Joined December 2025
Photo by LenSch (@LennScha)Photo by LenSch (@LennScha)Photo by LenSch (@LennScha)Photo by LenSch (@LennScha)Photo by LenSch (@LennScha)Photo by LenSch (@LennScha)Photo by LenSch (@LennScha)Photo by LenSch (@LennScha)Photo by LenSch (@LennScha)Photo by LenSch (@LennScha)
I hope it can remove my Weekly Fable limit
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! - ๐—›๐—ผ๐˜„ ๐—ฒ๐—ณ๐—ณ๐—ถ๐—ฐ๐—ถ๐—ฒ๐—ป๐˜ ๐—ถ๐˜€ ๐—ถ๐˜? 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. - ๐—›๐—ผ๐˜„ ๐—ด๐—ผ๐—ผ๐—ฑ ๐—ถ๐˜€ ๐—ถ๐˜? 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. - ๐—›๐—ผ๐˜„ ๐—ฑ๐—ผ๐—ฒ๐˜€ ๐—ถ๐˜ ๐˜„๐—ผ๐—ฟ๐—ธ? 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. ๐Ÿ‘‰ Blog: pruna.ai/blog/p-q-image-2.1-โ€ฆ ๐Ÿค— Open Weights: huggingface.co/PrunaAI/P-Q-Iโ€ฆ โšก๏ธ ComfyUI: huggingface.co/PrunaAI/P-Q-Iโ€ฆ
1
8
344
Seems like there are endless possibilities with this model
Introducing P-Video-2-Pro-Replace, based on @MiniMax_AI H3! ๐ŸŽฌ 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: - ๐—ฃ๐—ฟ๐—ถ๐—ฐ๐—ถ๐—ป๐—ด: Starting from $0.05/s at 480p - ๐—ฆ๐—ฝ๐—ฒ๐—ฒ๐—ฑ: ~1.5โ€“2 minutes for a 10-second video - ๐—ฅ๐—ฒ๐—ณ๐—ฒ๐—ฟ๐—ฒ๐—ป๐—ฐ๐—ฒ๐˜€: Replace up to two people using reference images - ๐——๐˜‚๐—ฟ๐—ฎ๐˜๐—ถ๐—ผ๐—ป: Supports videos up to 120 seconds Available via our inference partners @runware, @wavespeed_ai, Sociaro, @TellersAI, @WiroAI, @Segmind_ai, @replicate, and @eachlabs ๐Ÿ“š Model docs: docs.api.pruna.ai/guides/modโ€ฆ ๐Ÿงฉ Try the model through the API or Playground: dashboard.pruna.ai/login
2
11
1,071
P-H3-Image is really good at editing btw
1
14
909
I guess the next alien movie should use our model for ideation phase
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-imageโ€ฆ
3
189
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-imageโ€ฆ
2
6
1
14
675
LenSch retweeted
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. - ๐—›๐—ผ๐˜„ ๐—ฒ๐—ณ๐—ณ๐—ถ๐—ฐ๐—ถ๐—ฒ๐—ป๐˜ ๐—ถ๐˜€ ๐—ถ๐˜? 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. - ๐—›๐—ผ๐˜„ ๐—ด๐—ผ๐—ผ๐—ฑ ๐—ถ๐˜€ ๐—ถ๐˜? 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. -๐—›๐—ผ๐˜„ ๐—ฑ๐—ผ๐—ฒ๐˜€ ๐—ถ๐˜ ๐˜„๐—ผ๐—ฟ๐—ธ? 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. ๐Ÿ“„ Tech Report: pruna.ai/blog/oss-p-h3-imageโ€ฆ ๐Ÿค— @huggingface Open Weights: huggingface.co/PrunaAI/P-H3-โ€ฆ ๐Ÿ‘‰ @ComfyUI Native Support: huggingface.co/PrunaAI/P-H3-โ€ฆ
107
175
58
1,620
163,749
Right now every top image model is rl'd a little bit too much. We are releasing P-H3-Image at @PrunaAI, built on @MiniMax_AI H3. Not perfect, but the images definitely look real. Oh and it can do image editing. Day-0 support in ComfyUI and diffusers: huggingface.co/PrunaAI/P-H3-โ€ฆ
3
2
1
79
6,267
Video Upscaling is now basically free I guess
Introducing P-Video-Upscale! ๐ŸŽฌ 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: โ€ข ๐—ฃ๐—ฟ๐—ถ๐—ฐ๐—ถ๐—ป๐—ด: Starting from $0.01/s at 720p โ€ข ๐—ฆ๐—ฝ๐—ฒ๐—ฒ๐—ฑ: ~1.7s per second of output video, depending on resolution โ€ข ๐—™๐—ฟ๐—ฎ๐—บ๐—ฒ ๐—ฟ๐—ฎ๐˜๐—ฒ: Keep the original or interpolate up to 60 fps โ€ข ๐—ง๐˜‚๐—ฟ๐—ฏ๐—ผ ๐—บ๐—ผ๐—ฑ๐—ฒ: 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. ๐Ÿ“š Model docs: docs.api.pruna.ai/guides/modโ€ฆ ๐Ÿงฉ Try the model through the API or Playground: dashboard.pruna.ai/login
2
8
153
LenSch retweeted
It's almost time, Munich! Tomorrow, join us for Hacktoberfest with @MLHacks! We're hosting a casual meetup at the Pruna office on October 29th! Come grab a pizza, have a drink, meet other developers, and chat about open source, side projects, or whatever you're building. No talks or pitches, just a relaxed evening with the local community. ๐Ÿ“ Pruna office, Munich ๐Ÿ“… October 29, 6โ€“9 PM Hope to see you there! ๐Ÿ‘‰ Sign up: events.mlh.com/events/15374-โ€ฆ
2
7
24
1,293
LenSch retweeted
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! - ๐—›๐—ผ๐˜„ ๐—ฒ๐—ณ๐—ณ๐—ถ๐—ฐ๐—ถ๐—ฒ๐—ป๐˜ ๐—ถ๐˜€ ๐—ถ๐˜? 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. - ๐—›๐—ผ๐˜„ ๐—ด๐—ผ๐—ผ๐—ฑ ๐—ถ๐˜€ ๐—ถ๐˜? 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. - ๐—›๐—ผ๐˜„ ๐—ฑ๐—ผ๐—ฒ๐˜€ ๐—ถ๐˜ ๐˜„๐—ผ๐—ฟ๐—ธ? 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. ๐Ÿค— Open Weights: huggingface.co/PrunaAI/P-Q-Iโ€ฆ ๐Ÿ‘‰ HF Space: huggingface.co/spaces/PrunaAโ€ฆ
15
39
6
221
18,602
LenSch retweeted
P-Video-2-Pro-Avatar is #1 in overall human ratings, at a fraction of the cost and in seconds. - Quality: #1 of 10 models at 768p - Cost: 7ร— cheaper, just $0.02/s vs $0.14/s at 480p - Speed: 3ร— faster, just ~9.7s for a 10s clip at 480p - # 1 for music videos at 768p and #2 at 480p Across both Quality ร— Price and Quality ร— Speed, P-Video-2-Pro-Avatar stands out in the high-quality, low-cost, fast-generation region. From UGC ads to music videos, create high-quality talking avatars without compromising on speed or budget. Benchmarked by @RapidataAI. ๐Ÿงฉ API & Playground: buff.ly/OHtx3eM ๐Ÿ“š Documentation: buff.ly/bHQHKV0 ๐Ÿ“Š P-Bench: buff.ly/Fk54Z2K
18
14
5
56
3,363
LenSch retweeted
I can't believe what they say on this talk show ๐Ÿ‘€ By P-Video-2-Pro-Avatar
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! โ€ข ๐—ฃ๐—ฟ๐—ถ๐—ฐ๐—ถ๐—ป๐—ด: $0.02/s at 480p ยท $0.04/s at 768p โ€ข ๐—ฆ๐—ฝ๐—ฒ๐—ฒ๐—ฑ: ~0.97 s at 480p ยท ~2.2 s at 768p per second of output video โ€ข ๐—œ๐—ป๐—ฝ๐˜‚๐˜: One portrait with a text script or uploaded audio โ€ข ๐—ฉ๐—ผ๐—ถ๐—ฐ๐—ฒ๐˜€: 30 voices across 10 languages โ€ข ๐——๐˜‚๐—ฟ๐—ฎ๐˜๐—ถ๐—ผ๐—ป: 1sโ€“3min at 24 fps, in 480p or 768p โ€ข ๐—–๐—ผ๐—ป๐˜๐—ฟ๐—ผ๐—น: 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. ๐Ÿ“š Model docs: docs.api.pruna.ai/guides/modโ€ฆ ๐Ÿงฉ Try the model through the API or Playground: dashboard.pruna.ai/login
1
7
11
447
We at @PrunaAI are launching our new Avatar model. Super high quality and really cheap. $0.02/s at 480p, $0.04/s at 768p Oh and it is also super fast, as always! Right now 50% off Audio from @ElevenLabs
2
8
261
Awesome model, awesome video
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! โ€ข ๐—ฃ๐—ฟ๐—ถ๐—ฐ๐—ถ๐—ป๐—ด: $0.02/s at 480p ยท $0.04/s at 768p โ€ข ๐—ฆ๐—ฝ๐—ฒ๐—ฒ๐—ฑ: ~0.97 s at 480p ยท ~2.2 s at 768p per second of output video โ€ข ๐—œ๐—ป๐—ฝ๐˜‚๐˜: One portrait with a text script or uploaded audio โ€ข ๐—ฉ๐—ผ๐—ถ๐—ฐ๐—ฒ๐˜€: 30 voices across 10 languages โ€ข ๐——๐˜‚๐—ฟ๐—ฎ๐˜๐—ถ๐—ผ๐—ป: 1sโ€“3min at 24 fps, in 480p or 768p โ€ข ๐—–๐—ผ๐—ป๐˜๐—ฟ๐—ผ๐—น: 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. ๐Ÿ“š Model docs: docs.api.pruna.ai/guides/modโ€ฆ ๐Ÿงฉ Try the model through the API or Playground: dashboard.pruna.ai/login
6
179
LenSch retweeted
Munich, join us for Hacktoberfest with @MLHacks ! We're hosting a casual meetup at the Pruna office on October 29! Come grab a pizza, have a drink, meet other developers, and chat about open source, side projects, or whatever you're building. No talks or pitches, just a relaxed evening with the local community. ๐Ÿ“ Pruna office, Munich ๐Ÿ“… October 29, 6โ€“9 PM Hope to see you there! ๐Ÿ‘‰ Sign up: events.mlh.com/events/15374-โ€ฆ
10
6
31
1,286
I donโ€™t think Europeans fully appreciate what is happening to the European Union right now. The EU is under an extraordinary, multi-front assault, both from outside and from within. And I struggle to think of another period in its history when so many powerful actors had an interest in weakening it simultaneously. Russia has spent years waging hybrid warfare against Europe. Weaponised migration, sabotage, cyberattacks, coordinated disinformation campaigns, bot networks and political interference. The objective is clear: undermine trust in democratic institutions, deepen social divisions and weaken European unity. China has different motivations, primarily economic and geopolitical. A fragmented Europe is easier to pressure, easier to negotiate with individually and less capable of defending its economic interests. And then there is the United States. Perhaps the most disturbing development of all. Under Trump and MAGA, a country that helped rebuild the old continent and then spent decades supporting European integration now has an administration openly hostile to much of what the EU represents. Its own National Security Strategy even calls for cultivating resistance to Europeโ€™s current political direction. Think about that for a moment. Meanwhile, within Europe, parts of the far right and far left amplify these divisions, whether through ideological alignment, political opportunism or outright sympathy for authoritarian regimes. This doesnโ€™t mean Russia, China and MAGA are all following some jointly coordinated master plan. They donโ€™t have to. Their interests increasingly overlap, and Europeโ€™s internal divisions make their work considerably easier. What makes this particularly alarming is what is actually at stake. For all its flaws, the EU remains one of the worldโ€™s most consequential projects built around liberal democracy, the rule of law, individual freedoms and cooperation between nations. At a time when authoritarianism is gaining ground and even longstanding democracies are showing disturbing tendencies, that matters enormously. Europe is far from perfect. Its bureaucracy, indecision and inability to act decisively are real problems. But the answer cannot be to retreat into 27 competing nation-states, each too small to meaningfully influence a world increasingly dominated by continental powers. Quite the opposite. Europe needs deeper integration, stronger common institutions, genuine strategic autonomy and the political courage to defend its interests and values. Because fragmentation is precisely what so many external actors want. And perhaps thatโ€™s the central irony of our time: people are being deliberately manipulated into believing that the reverse is true โ€” that national identity and sovereignty can only be protected by weakening European cooperation. In reality, a divided Europe is less sovereign, less secure and far easier for outside powers to pressure. Therefore the very thing that will make Europe stronger is the thing its adversaries are working hardest to prevent. A united Europe is a geopolitical power. A divided Europe is a collection of countries waiting to be played against one another.
648
1,933
216
6,366
367,409
Really no reason to use any other model for i2v
p-video-2-pro is now the undisputed king of video models on @DesignArena. #1 ELO, Only model on Pareto plots
4
68
LenSch retweeted
Munich, join us for Hacktoberfest with @MLHacks ! We're hosting a casual meetup at the Pruna office on October 29! Come grab a pizza, have a drink, meet other developers, and chat about open source, side projects, or whatever you're building. No talks or pitches, just a relaxed evening with the local community. ๐Ÿ“ Pruna office, Munich ๐Ÿ“… October 29, 6โ€“9 PM Hope to see you there! ๐Ÿ‘‰ Sign up: events.mlh.com/events/15374-โ€ฆ
3
9
1
24
1,417
P-Video-2 Pro Reference-to-Video is now LIVE on WaveSpeed AI! Up to 9 images. Up to 3 reference videos. Up to 3 audio references. Control the look, motion, and direction of every scene, all from your references. Built with @PrunaAI 's P-Video-2 Pro.
11
8
1
43
2,375
like many people, i've wondered my whole life if I could beat a horse sized duck in a Mortal Kombat fight ... you can find out too with P-Video-2-Pro-Reference
Introducing P-Video-2-Pro-Reference based on @MiniMax_AI H3! ๐ŸŽฌ 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. โ€ข ๐—œ๐—ป๐—ฝ๐˜‚๐˜: Text prompt with image and/or video references, plus optional audio โ€ข ๐—ฅ๐—ฒ๐—ณ๐—ฒ๐—ฟ๐—ฒ๐—ป๐—ฐ๐—ฒ๐˜€: Up to 9 images, 3 videos, and 3 audio files โ€ข ๐——๐˜‚๐—ฟ๐—ฎ๐˜๐—ถ๐—ผ๐—ป: 5โ€“15s at 480p or 768p โ€ข ๐—ฃ๐—ฟ๐—ถ๐—ฐ๐—ถ๐—ป๐—ด: Output starting at $0.015/s in Cost mode, with reference inputs billed separately โ€ข ๐—–๐—ผ๐—ป๐˜๐—ฟ๐—ผ๐—น: 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 ๐Ÿ“š Model docs: docs.api.pruna.ai/guides/modโ€ฆ ๐Ÿงฉ API: dashboard.pruna.ai/login
1
4
9
209