# Image to Video Models: Open-Weight AI Source: https://savrn.com/models/tasks/image-to-video Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- SAVRN Model Hub · Models by Task # Image to Video Models 36 open-weight image to video models in the SAVRN Model Hub, with LTX.io, ARC Lab, Tencent and Joey publishing the most. 36Models 26Publishers 1.9B to 18.9BParameter range 5Licenses ## SAVRN's Take Hand one of these models a still frame and it returns a clip, some with sound: LTX-2 generates video and audio in a single model, and MiniMax H3 adds native stereo audio at up to 2K and 15 seconds. LTX.io publishes five of the 18, more than anyone else, yet downloads run elsewhere. The Comfy Org repackaging of Wan 2.2 leads at 5,791,673 a month, ahead of LTX-2.5 at 1,590,087 and Minimax-h3-Turbo at 1,531,171. A repackaging outdrawing every base checkpoint means people run these on their own machines. Only two of the 18 state a size, at opposite ends: LTX-Video at 1.9B needs 4.6 GB at 16-bit, 2.3 GB at 8-bit and 1.2 GB at 4-bit, and LTX-2 at 18.9B needs 45.3 GB, 22.7 GB and 11.3 GB at the same precisions. Neither forces a hardware decision: both fit on one MI300X at $1.85 an hour, the cheapest we track. The other 16 list no size, so measure the footprint before committing a rack. Thirteen of the 18 carry a license recorded only as other and two state none, so for 15 the first job is learning what the publisher permits. Three are Apache 2.0, two of them in the download top three, Wan 2.2 and Minimax-h3-Turbo, and for clips sold to customers that removes a review the other 15 do not. Every LTX.io entry sits in that other column, and LTX-2.5 is gated too. Weigh whether you need audio, whether the footprint fits your cards, and whether you want the publisher's build or a repackaging. SAVRN Research, 2026-09-18 ## Most Downloaded | Model | Publisher | Parameters | License | Monthly downloads | Cheapest GPUs at 16-bit | | --- | --- | --- | --- | --- | --- | | [Wan-2.2](https://savrn.com/models/wan-2-2) | Comfy Org | — | apache-2.0 | 8.2M | — | | [Wan_2.2_ComfyUI_Repackaged](https://savrn.com/models/wan-2-2-comfyui-repackaged) | Comfy Org | — | apache-2.0 | 8.2M | — | | [LTX-2.5](https://savrn.com/models/ltx-2-5) | LTX.io | — | other | 2.1M | — | | [LTX-2.5](https://savrn.com/models/ltx-2-5-2) | Comfyicu | — | other | 1.8M | — | | [MiniMax-H3-GGUF](https://savrn.com/models/minimax-h3-gguf) | Jay | — | other | 1M | — | | [LTX-2.3](https://savrn.com/models/ltx-2-3) | LTX.io | — | other | 991.2k | — | | [LTX-Video](https://savrn.com/models/ltx-video) | LTX.io | 1.9B | other | 762k | 1x MI300X, $1.85/hr | | [LTX-2.3-fp8](https://savrn.com/models/ltx-2-3-fp8) | LTX.io | — | other | 525.8k | — | | [LTX-2](https://savrn.com/models/ltx-2-2) | LTX.io | 18.9B | other | 324.4k | 1x MI300X, $1.85/hr | | [LTX-2.3-GGUF](https://savrn.com/models/ltx-2-3-gguf) | Unsloth AI | — | other | 283.8k | — | ## Licenses | License | Models | Commercial use | | --- | --- | --- | | other | 19 | Read the license | | [apache-2.0](https://savrn.com/models/licenses/apache-2-0) | 9 | Yes | | not stated | 6 | Not stated | | [mit](https://savrn.com/models/licenses/mit) | 1 | Yes | | [cc-by-nc-4.0](https://savrn.com/models/licenses/cc-by-nc-4-0) | 1 | Not without separate permission | ## Who Publishes Them | Publisher | Models | | --- | --- | | [LTX.io](https://savrn.com/model-publishers/lightricks) | 5 | | [ARC Lab, Tencent](https://savrn.com/model-publishers/tencentarc) | 4 | | [Joey](https://savrn.com/model-publishers/joeygambino) | 2 | | [Daniel](https://savrn.com/model-publishers/ibyteohdear) | 2 | | [Comfy Org](https://savrn.com/model-publishers/comfy-org) | 2 | | [AIGC Singularity](https://savrn.com/model-publishers/warmbloodaban) | 1 | ## All 36 Models Model · Image to video ### [Wan_2.2_ComfyUI_Repackaged](https://savrn.com/models/wan-2-2-comfyui-repackaged) [Comfy Org](https://savrn.com/model-publishers/comfy-org) Repackaged model files for ComfyUI. - https://huggingface.co/nvidia/ChronoEdit-14B-Diffusers - https://huggingface.co/Wan-AI/Wan2.2-Animate-14B - https://huggingface.co/alibaba-pai/Wan2.2-Fun-A14B-Control-Camera - https://huggingface.co/alibaba-pai/Wan2.2-Fun-A14B-Control - https://huggingface.co/alibaba-pai/Wan2.2-Fun-5B-Control - https://huggingface.co/alibaba-pai/Wan2.2-Fun-5B-InP - https://huggingface.co/alibaba-pai/Wan2.2-Fun-A14B-InP - https://huggingface.co/alibaba-pai/Wan2.2-VACE-Fun-A14B - https://huggingface.co/Wan-AI/Wan2.2-I2V-A14B - https://huggingface.co/Wan-AI/Wan2.2-S2V-14B - https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B - https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B… Open weights apache-2.0 diffusion-single-file [View model](https://savrn.com/models/wan-2-2-comfyui-repackaged) Model · Image to video ### [LTX-2.5](https://savrn.com/models/ltx-2-5) [LTX.io](https://savrn.com/model-publishers/lightricks) LTX-2.5 is an open world model with open weights, built for local execution and fine-tuning. Its established use is generating synchronized, high-fidelity video and audio from text, image, and video inputs; applicability to emerging domains such as robotics and physical AI is developing. Full control and customization — self-host on your own infrastructure. No per-generation billing, no per-seat lock-in, no forced API dependency. Revenue is measured across the whole entity, including subsidiaries and affiliates under common control. The full, binding terms live in LICENSE. - Native multishot generation — generate connected scenes in a single pass: multiple shots that hold character… Access requested at publisher other diffusion-single-file [View model](https://savrn.com/models/ltx-2-5) Model · Image to video ### [LTX-2.3](https://savrn.com/models/ltx-2-3) [LTX.io](https://savrn.com/model-publishers/lightricks) This model card focuses on the LTX-2.3 model, which is a significant update to the LTX-2 model with improved audio and visual quality as well as enhanced prompt adherence. LTX-2 was presented in the paper LTX-2: Efficient Joint Audio-Visual Foundation Model. If you want to dive in right to the code - it is available here. LTX-2.3 is a DiT-based audio-video foundation model designed to generate synchronized video and audio within a single model. It brings together the core building blocks of modern video generation, with open weights and a focus on practical, local execution. LTX-2.3 is accessible right away via the API Playground. You can use the models - full, distilled, upscalers and any… Open weights other diffusers [View model](https://savrn.com/models/ltx-2-3) Model · Image to video ### [LTX-Video](https://savrn.com/models/ltx-video) [LTX.io](https://savrn.com/model-publishers/lightricks) This model card focuses on the model associated with the LTX-Video model, codebase available here. LTX-Video is the first DiT-based video generation model capable of generating high-quality videos in real-time. It produces 30 FPS videos at a 1216×704 resolution faster than they can be watched. Trained on a large-scale dataset of diverse videos, the model generates high-resolution videos with realistic and varied content. You can use the model for purposes under the license: - 2B version 0.9: license - 2B version 0.9.1 license - 2B version 0.9.5 license - 2B version 0.9.6-dev license - 2B version 0.9.6-distilled license - 13B version 0.9.7-dev license - 13B version 0.9.7-dev-fp8 license… Open weights other 1.9B parameters diffusers [View model](https://savrn.com/models/ltx-video) Model · Image to video ### [LTX-2](https://savrn.com/models/ltx-2-2) [LTX.io](https://savrn.com/model-publishers/lightricks) This model card focuses on the LTX-2 model, as presented in the paper LTX-2: Efficient Joint Audio-Visual Foundation Model. The codebase is available here. LTX-2 is a DiT-based audio-video foundation model designed to generate synchronized video and audio within a single model. It brings together the core building blocks of modern video generation, with open weights and a focus on practical, local execution. LTX-2 is accessible right away via the following links: You can use the models - full, distilled, upscalers and any derivatives of the models - for purposes under the license. We recommend you use the built-in LTXVideo nodes that can be found in the ComfyUI Manager. For manual… Open weights other 18.9B parameters diffusers [View model](https://savrn.com/models/ltx-2-2) Model · Image to video ### [Minimax-h3_Singularity](https://savrn.com/models/minimax-h3-singularity) [AIGC Singularity](https://savrn.com/model-publishers/warmbloodaban) Minimax-h3Singularity is a comprehensive fine-tuned fusion model specialized in enhancing the capabilities of MiniMax-H3. Designed as a versatile multimodal video generation model, it natively supports Text-to-Video (T2V), Image-to-Video (I2V), Reference-to-Video (Ref2V), and Video-to-Video (V2V) workflows within ComfyUI. Built upon a strategic fusion of key checkpoints (including ref, fl, b25-49, etc.), this model underwent deep high-step fine-tuning. To preserve the original model's foundational strengths and broad generalization while solving artifacts introduced by high-step training, we spent 3 full days on precise model pruning and weight optimization. The result is a clean, sharp… Open weights apache-2.0 minimax-h3 [View model](https://savrn.com/models/minimax-h3-singularity) Model · Image to video ### [Wan-2.2](https://savrn.com/models/wan-2-2) [Comfy Org](https://savrn.com/model-publishers/comfy-org) Repackaged model files for ComfyUI. - https://huggingface.co/nvidia/ChronoEdit-14B-Diffusers - https://huggingface.co/Wan-AI/Wan2.2-Animate-14B - https://huggingface.co/alibaba-pai/Wan2.2-Fun-A14B-Control-Camera - https://huggingface.co/alibaba-pai/Wan2.2-Fun-A14B-Control - https://huggingface.co/alibaba-pai/Wan2.2-Fun-5B-Control - https://huggingface.co/alibaba-pai/Wan2.2-Fun-5B-InP - https://huggingface.co/alibaba-pai/Wan2.2-Fun-A14B-InP - https://huggingface.co/alibaba-pai/Wan2.2-VACE-Fun-A14B - https://huggingface.co/Wan-AI/Wan2.2-I2V-A14B - https://huggingface.co/Wan-AI/Wan2.2-S2V-14B - https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B - https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B… Open weights apache-2.0 diffusion-single-file [View model](https://savrn.com/models/wan-2-2) Model · Image to video ### [LTX-2.5](https://savrn.com/models/ltx-2-5-2) [Comfyicu](https://savrn.com/model-publishers/comfyicu) LTX-2.5 is an open world model with open weights, built for local execution and fine-tuning. Its established use is generating synchronized, high-fidelity video and audio from text, image, and video inputs; applicability to emerging domains such as robotics and physical AI is developing. Full control and customization — self-host on your own infrastructure. No per-generation billing, no per-seat lock-in, no forced API dependency. Revenue is measured across the whole entity, including subsidiaries and affiliates under common control. The full, binding terms live in LICENSE. - Native multishot generation — generate connected scenes in a single pass: multiple shots that hold character… Open weights other diffusion-single-file [View model](https://savrn.com/models/ltx-2-5-2) Model · Image to video ### [MiniMax-H3-GGUF](https://savrn.com/models/minimax-h3-gguf) [Jay](https://savrn.com/model-publishers/abiray) This repository (Abiray/MiniMax-H3-GGUF) provides GGUF quantized versions and necessary component files for the MiniMax H3 model. MiniMax H3 is a general-purpose, omni-modal generative system that supports unified understanding of multimodal contexts composed of text, images, video, and audio. It can generate video with native stereo audio at resolutions up to 2K and durations of up to 15 seconds. If you are looking for a smaller model with the same great quality that fits better on consumer-tier GPUs, please check out the MiniMax-H3-Pruned-GGUF repository. The pruned architecture is compressed down to 8.9 GB – 21.6 GB, bringing MiniMax H3 execution directly to consumer hardware. This… Open weights other [View model](https://savrn.com/models/minimax-h3-gguf) Model · Image to video ### [LTX-2.3-fp8](https://savrn.com/models/ltx-2-3-fp8) [LTX.io](https://savrn.com/model-publishers/lightricks) This is the FP8 versions of the LTX-2.3 model. All information below is derived from the base model. This model card focuses on the LTX-2.3 model, which is a significant update to the LTX-2 model with improved audio and visual quality as well as enhanced prompt adherence. LTX-2 was presented in the paper LTX-2: Efficient Joint Audio-Visual Foundation Model. If you want to dive in right to the code - it is available here. LTX-2.3 is a DiT-based audio-video foundation model designed to generate synchronized video and audio within a single model. It brings together the core building blocks of modern video generation, with open weights and a focus on practical, local execution. LTX-2.3 is… Open weights other diffusers [View model](https://savrn.com/models/ltx-2-3-fp8) Model · Image to video ### [LTX-2.3-GGUF](https://savrn.com/models/ltx-2-3-gguf) [Unsloth AI](https://savrn.com/model-publishers/unsloth) This is a GGUF quantized version of LTX-2.3. unsloth/LTX-2.3-GGUF uses Unsloth Dynamic 2.0 methodology for SOTA performance. - Important layers are upcasted to higher precision. - Uses tooling from ComfyUI-GGUF by city96. There are two sets of GGUF's published. One for the dev model and one for the distilled. The distilled model is optimized for few step generation, think 4-8 steps. dev on the other hand needs more steps at least 20, but you get better outputs. The distilled variant is useful as a drafting model or a refining model. In fact the workflow published below, uses the distilled lora on top of the dev model to refine the intial output. Download the mp4 in the repo and open it with… Open weights other ggml [View model](https://savrn.com/models/ltx-2-3-gguf) Model · Image to video ### [MiniMax-H3-encoder-GGUF](https://savrn.com/models/minimax-h3-encoder-gguf) [Joey](https://savrn.com/model-publishers/joeygambino) GGUF quantizations of the Qwen3-VL-32B vision-language text encoder used by MiniMax-H3 in ComfyUI. The H3 DiT quants are here: joeygambino/MiniMax-H3-GGUF. You need one file from each repo to run H3 — the DiT alone will not generate anything. Load these encoders with H3 Clip Loader (Any) from not the stock CLIPLoaderGGUF node. The H3 text encoder is a truncated Qwen3-VL-32B - 50 layers, no final norm, no lmhead - and its vision tower ships separately as the -mmproj-F16.gguf sidecar. Stock ComfyUI-GGUF only merges an mmproj when the encoder's architecture is qwen2vl; Qwen3-VL reports qwen3vl, so the sidecar is never merged at all, and the resulting missing vision tensors surface as a… Open weights gguf [View model](https://savrn.com/models/minimax-h3-encoder-gguf) Model · Image to video ### [MiniMax-H3-GGUF](https://savrn.com/models/minimax-h3-gguf-3) [Leejet](https://savrn.com/model-publishers/leejet) The license of the quantized files follows the license of the original model: These files are converted using https://github.com/leejet/stable-diffusion.cpp This model can be used with stable-diffusion.cpp. For setup instructions and usage details, please refer to: To use this model in ComfyUI, first install the following custom node: An example ComfyUI workflow is available here: src="https://huggingface.co/leejet/MiniMax-H3-GGUF/resolve/main/assets/example.mp4" controls muted Open weights [View model](https://savrn.com/models/minimax-h3-gguf-3) Model · Image to video ### [MiniMax-H3-GGUF](https://savrn.com/models/minimax-h3-gguf-4) [Bálint Molnár-Kaló](https://savrn.com/model-publishers/molbal) This repository (molbal/MiniMax-H3-GGUF) provides GGUF quantized versions and necessary component files for the MiniMax H3 model. MiniMax H3 is a general-purpose, omni-modal generative system that supports unified understanding of multimodal contexts composed of text, images, video, and audio. It can generate video with native stereo audio at resolutions up to 2K and durations of up to 15 seconds. This repository includes quantized versions of both the FL2VA (First-and-last-frame mode) and Ref2VA (Omni-reference mode) base models. The FL2VA builds are pruned to FP8 first and then quantized to GGUF. minimaxh3fl2vaprunedfp8Q40.gguf (11.4 GB) minimaxh3fl2vaprunedfp8Q80.gguf (20.2 GB)… Open weights other [View model](https://savrn.com/models/minimax-h3-gguf-4) Model · Image to video ### [Lightricks-LTX-2-DISTILLED-10-Eros](https://savrn.com/models/lightricks-ltx-2-distilled-10-eros) [Daniel](https://savrn.com/model-publishers/ibyteohdear) LTX2.5 temp v3 has 10eros audio while v2 is sulphur audio, hopefully the 85 can fix it if you have audio problems,LTX2.5DEV10Eros15r512.safetensors seems most stable LTX2.3DISTILLEDBAKEDLTXSULPHURSTYLEIS10Erosr256.safetensors this seems to be the best for stacking lora i'm just guessing the strength and not 100% sure which reason is best 10 Eros v1.4 Changelog: Built off 1.3 and bringing back explicit prompting and motion hopefully without any kind of anatomy redraw or negative tendency. Still requires intense prompt refinement. This version is set up to be trained on to fix it into a real base, it doesn't depict anatomy well but it also isn't confused by it which is priority for the first… Open weights other diffusers [View model](https://savrn.com/models/lightricks-ltx-2-distilled-10-eros) Model · Image to video ### [MiniMax-H3-curve-GGUF](https://savrn.com/models/minimax-h3-curve-gguf) [Joey](https://savrn.com/model-publishers/joeygambino) GGUF quantizations of MiniMax-H3's 33B video+audio DiTs, built from MiniMax's pruned checkpoints. Same model, same quant tiers as the original-form repo, about 40% smaller - and a Q80 that fits a 24 GB card. fl2va = text/first-last-frame to video+audio (T2V and I2V). ref2va = reference-conditioned generation (identity from up to 9 images, 3 videos with soundtracks, 3 voice clips). Runs in ComfyUI with ComfyUI-GGUF plus a one-line architecture patch (node pack: ComfyUI-H3-Multishot; workflows: On anything older these will not load at all, because the shape of the modulation weights changed and older builds do not know how to read them. That is the only catch - everything else is a drop-in… Open weights other minimax-h3 [View model](https://savrn.com/models/minimax-h3-curve-gguf) Model · Image to video ### [Lightricks-LTX-2](https://savrn.com/models/lightricks-ltx-2) [Daniel](https://savrn.com/model-publishers/ibyteohdear) LTX-2.5 is an open world model with open weights, built for local execution and fine-tuning. Its established use is generating synchronized, high-fidelity video and audio from text, image, and video inputs; applicability to emerging domains such as robotics and physical AI is developing. Full control and customization — self-host on your own infrastructure. No per-generation billing, no per-seat lock-in, no forced API dependency. Revenue is measured across the whole entity, including subsidiaries and affiliates under common control. The full, binding terms live in LICENSE. - Native multishot generation — generate connected scenes in a single pass: multiple shots that hold character… Open weights other diffusion-single-file [View model](https://savrn.com/models/lightricks-ltx-2) Model · Image to video ### [LTX-2.3-GGUF](https://savrn.com/models/ltx-2-3-gguf-2) [QuantStack](https://savrn.com/model-publishers/quantstack) This GGUF file is a direct conversion of Lightricks/LTX-2.3 is a quantized model, all original licensing terms and usage restrictions remain in effect. Open weights other gguf [View model](https://savrn.com/models/ltx-2-3-gguf-2) Model · Image to video ### [MiniMax-H3-PTD-LoRAs](https://savrn.com/models/minimax-h3-ptd-loras) [Taobao Content AI](https://savrn.com/model-publishers/taobao-content-ai) We apply PTD (Parametric Trajectory Distillation) to MiniMax-H3, distilling the Ref2VA (reference-image → video + audio) trajectory into a few-step student. We release an 8-step and a 4-step accelerator for the Ref2VA task. Unlike a single shared acceleration LoRA, PTD trains one independent low-rank adapter per inference step ("per-hop" LoRA) on the diffusion backbone, on top of the per-interval output heads introduced by Parallel Decoding Distillation (PDD). At inference, each denoising step selects its own hop's adapter and fuses that step's output head, so an 8-hop checkpoint runs in 8 transformer evaluations (NFE) and a 4-hop checkpoint in 4. Each checkpoint carries its configuration… Open weights other minimax-h3 [View model](https://savrn.com/models/minimax-h3-ptd-loras) Model · Image to video ### [MiniMax-H3-ORB360-CardSpin](https://savrn.com/models/minimax-h3-orb360-cardspin) [MATLOWAI](https://savrn.com/model-publishers/matlowai) Rank-32 LoRAs for MiniMax-H3 Ref2VA. Give it a photo, get a smooth clockwise 360-degree camera orbit around the frozen subject (ORB360CW), or, with the CardSpin files, turn the photo in space like a thin physical card (ORB360CARDSPIN). Both CardSpin files can still orbit with the orbit prompt, but they are noticeably softer; see Powered by MiniMax H3. poster="https://huggingface.co/MATLOWAI/MiniMax-H3-ORB360-CardSpin/resolve/main/assets/whitecatcardspinv2step50poster.jpg"> minimaxh3orb360cardspinv2step50.safetensors, one reference image (examples/whitecat.png), the prompt in prompts/cardspincaption.txt, 1024 x 768, 124 frames, 20 steps, seed 20260926.… Open weights other minimax-h3 [View model](https://savrn.com/models/minimax-h3-orb360-cardspin) Model · Image to video ### [flux3-agibot-looped](https://savrn.com/models/flux3-agibot-looped) [Song](https://savrn.com/model-publishers/jinyan0924) Looped Diffusion Transformer (Chng et al., 2026, arXiv:2609.40305) retrofit of Jinyan0924/flux3-agibot-videoft (itself a full fine-tune of black-forest-labs/flux-3-action-base): the 33 joint blocks are split 12 / 9 / 12, the middle 9 are run N = 4 times with head-wise gated attention, and every exit is trained with deep supervision. Task: k past head-camera frames + caption → 33 future frames at 15 fps, Val loss (EMA, N = 4, lower is better; k = number of context frames): r1 step 2500 k1 0.0787 / k9 0.0654; r2 step 4000 k1 0.0783 / k9 0.0651 (the step-4500 val pass was interrupted by the crash that ended the run, so the last val point is step 4000). Test-split PSNR / SSIM / LPIPS / FVD and… Open weights other [View model](https://savrn.com/models/flux3-agibot-looped) Model · Image to video ### [AI-Migos-Video-Hotel-Lobby-Video](https://savrn.com/models/ai-migos-video-hotel-lobby-video) [AI Migos Video - Hotel Lobby Video](https://savrn.com/model-publishers/ai-migos-video) Turn two ordinary photos into the viral "Hotel Lobby" / Migos AI video with your faces. Same orange booth, same moves, same beat. No prompts, no source clip, no editing. Renders in about 3 minutes, and your first 5-second preview is free. Every clip below started as two separate photos. Sound on. Two men in their seventies with the full Quavo and Takeoff choreography. Two photos taken years apart, one performance. Office headshots in, rap duo out. More examples (couples, best friends, cats, the same person twice) on the Migos AI Video Generator page. "Migos AI", "Hotel Lobby AI" and "AI rap duo" all name the same trend: AI videos that recreate Quavo and Takeoff's 2022 performance of Hotel… Open weights other other [View model](https://savrn.com/models/ai-migos-video-hotel-lobby-video) Model · Image to video ### [comfy-MiniMax-H3-workflows](https://savrn.com/models/comfy-minimax-h3-workflows) [Javano](https://savrn.com/model-publishers/javawock7618) Optimized ComfyUI workflows for MiniMax-H3, featuring INT8 inference, native Block Sparse Attention, Spectrum, Lightx2v LoRA, Turbo-LoRA, native Extend, Fun ControlNet Union V2V control, Face Refine, TTS, Latent Upscaler, Bridge, and Group Bypass. Comfy-Org/MiniMax-H3 https://huggingface.co/Comfy-Org/MiniMax-H3 The workflows use the native Block Sparse Attention node for optimized MiniMax-H3 attention processing. ComfyUI-Spectrum-MiniMax-H3 https://github.com/xmarre/ComfyUI-Spectrum-MiniMax-H3 Optimized sampling and MiniMax-H3 inference acceleration. lightx2v/Minimax-h3-Turbo https://huggingface.co/lightx2v/Minimax-h3-Turbo Acceleration LoRA for reduced sampling steps.… Open weights minimax-h3 [View model](https://savrn.com/models/comfy-minimax-h3-workflows) Model · Image to video ### [cosmos-predict2.5-2b-agibot-mv-robocasa-pressbutton](https://savrn.com/models/cosmos-predict2-5-2b-agibot-mv-robocasa-pressbutton) [SeongyoungMoon](https://savrn.com/model-publishers/gom-sy) Private research checkpoints — Cosmos-Predict2.5-2B robot/multiview-agibot (frameinit) post-trained on RoboCasa CoffeePressButton 3-view renders (55 human demos, 704² → trained at 480², 81 frames/view @20 fps). 2026-10. iterXXXXXX/modelemabf16.pt — EMA weights (bf16) for inference with experiment 2brobocasacoffeeagibotframeinit (code/ holds the dataset/experiment files and mvinfer.py needed to reproduce; see code/HANDOFF.md). Research only (world-model video generation for IDM labelling / policy training). Round 1 (iter004000/, identity extrinsics) showed view collapse at t≥20 frames (3 views converging to one), seed-dependent. Round 2 restarts from the agibot base with real MuJoCo camera… Access requested at publisher other [View model](https://savrn.com/models/cosmos-predict2-5-2b-agibot-mv-robocasa-pressbutton) Model · Image to video ### [DreamX-Creator-gguf](https://savrn.com/models/dreamx-creator-gguf) [EvoAwaken Workshop](https://savrn.com/model-publishers/evoawaken-workshop) Community GGUF conversion of GD-ML/DreamX-Creator for the native CPU runtime in rust-model-inference. DreamX-Creator generates synchronized video and audio from a first frame and a text prompt. These files also contain the optional 2x video refiner components. Both files are required and must be used together. The runtime verifies their shared pair ID before inference. Build rust-model-inference, then run: Add --dry-run to validate the model pair and inspect the memory estimate without running generation. Full inference produces base video/audio/mux outputs and, with --refine, refined video/mux outputs. The pair is exported from the original DreamX-Creator checkpoint with the repository's… Open weights apache-2.0 [View model](https://savrn.com/models/dreamx-creator-gguf) Model · Image to video ### [GAE-D64-1B](https://savrn.com/models/gae-d64-1b) [ARC Lab, Tencent](https://savrn.com/model-publishers/tencentarc) (hiddensize=[768, 2048], depth=[28, 6]) over a 64-channel geometry-native latent, at 672×378 and V=81, with metric Plücker camera conditioning and Qwen3-0.6B text. This repo is self-contained for GAE-64 inference: codec, per-channel latent statistics, DA3 feature-level stats, and the flow transformer. The frozen DA3-GIANT encoder / DPT head comes from Or, after the files are in ckpts/: Image-to-video uses 50 Euler steps and CFG 2 with one reference view. - codec/ — safetensors + config.json - gae64.pt — drop-in checkpoint for gae.loadcodec - latentstatsgae64.pt — per-channel latent mean/std - da3statsgiant5ds.tar — DA3 feature-level normalization stats - transformer/ — flow safetensors +… Open weights pytorch [View model](https://savrn.com/models/gae-d64-1b) Model · Image to video ### [hunyuan-npu-models](https://savrn.com/models/hunyuan-npu-models) [Jiang Feng Zheng Ba](https://savrn.com/model-publishers/jiangfeng12) Modelos y app de Hunyuan NPU: generar vídeo con HunyuanVideo 1.5 y FastHunyuan 13B en local, en la NPU Hexagon v81 de los Snapdragon 8 Elite (Gen 5) — probado en un Nubia Z80 Ultra —, con stable-diffusion.cpp + ggml-hexagon. Proyecto personal, no comercial, hecho con mucho cariño y poca paciencia. Este proyecto no pretende competir con Nightmare Mobile de AbrahamPaulJ, que es la referencia para generar imagen y vídeo en la NPU de los Snapdragon, ni con Local Dream (xororz). Al contrario: sin ellos esto no existiría. El motor DiT viene de Local Dream, con parches de Nightmare Mobile, y todo corre sobre el Todo el mérito del trabajo duro es suyo; aquí sólo hemos atornillado HunyuanVideo… Open weights other [View model](https://savrn.com/models/hunyuan-npu-models) Model · Image to video ### [LIFT](https://savrn.com/models/lift) [Shengxiang Ji](https://savrn.com/model-publishers/overdog) We introduce LIFT, a unified image-to-video generation framework that complements camera control with Layout-In-FuTure control, enabling users to specify what should appear in a future view and where it should appear. Our models are built on Wan2.1-Fun-V1.1-1.3B-Control-Camera. Open weights apache-2.0 diffusers [View model](https://savrn.com/models/lift) Model · Image to video ### [Looking-Ahead](https://savrn.com/models/looking-ahead) [ARC Lab, Tencent](https://savrn.com/model-publishers/tencentarc) Open weights apache-2.0 [View model](https://savrn.com/models/looking-ahead) Model · Image to video ### [Prism](https://savrn.com/models/prism) [Shuyuan Tu](https://savrn.com/model-publishers/francisring) Prism:Dynamic Sparse Attention for Native 2K Joint Video-Audio Generation Model Training Shuyuan Tu 1, Qi Tian 2, Yinming Huang 1, Yue Wu 2, Xintong Han 2, Kaihang Pan 3, Weijie Kong 2, Jiangfeng Xiong 2, Jian-Wei Zhang 2, Zuxuan Wu 1, Yu-Gang Jiang 1 [ 1 Fudan University; 2 Tencent Hunyuan; 3 Zhejiang University] Native training joint video-audio generation models at higher resolutions empowers them to learn richer visual details and sharper motion dynamics. However, full attention incurs quadratic cost and, as resolution increases, spreads attention over increasingly redundant tokens, diluting learning signals for informative content and disrupting pretrained priors. Existing sparse… Open weights mit diffusers [View model](https://savrn.com/models/prism) Model · Image to video ### [ProAR](https://savrn.com/models/proar) [Shen Linghui](https://savrn.com/model-publishers/linghuishen) ProAR solves reasoning tasks by autoregressively generating a sequence of visual states. It equips autoregressive video models with two complementary components: - Outcome Guidance predicts a future goal frame to guide current-chunk generation. - Transition Guidance aligns the current representation with the clean next-chunk representation during training. ProAR is built upon Wan2.2-TI2V-5B. hf download LinghuiShen/ProAR \ --local-dir checkpoints/ProAR Open weights apache-2.0 [View model](https://savrn.com/models/proar) Model · Image to video ### [Ropedia-W0](https://savrn.com/models/ropedia-w0) [Ropedia](https://savrn.com/model-publishers/ropedia-ai) Open weights cc-by-nc-4.0 [View model](https://savrn.com/models/ropedia-w0) Model · Image to video ### [Wan-Alpha-I2V](https://savrn.com/models/wan-alpha-i2v) [Dong Haotian](https://savrn.com/model-publishers/htdong) Open weights apache-2.0 diffusers [View model](https://savrn.com/models/wan-alpha-i2v) Model · Image to video ### [wan2.2_14b_i2v_480p_lightning_nsfw_diffusers](https://savrn.com/models/wan2-2-14b-i2v-480p-lightning-nsfw-diffusers) [Jarosz](https://savrn.com/model-publishers/sebstian9191) We are excited to introduce Wan2.2, a major upgrade to our foundational video models. With Wan2.2, we have focused on incorporating the following innovations: This repository also includes our I2V-A14B model, designed for image-to-video generation, supporting both 480P and 720P resolutions. Built with a Mixture-of-Experts (MoE) architecture, it achieves more stable video synthesis with reduced unrealistic camera movements and offers enhanced support for diverse stylized scenes. Your browser does not support the video tag. If your research or project builds upon Wan2.1 or Wan2.2, we welcome you to share it with us so we can highlight it for the broader community. - Wan2.2 Text-to-Video - [x]… Open weights apache-2.0 14.3B parameters diffusers [View model](https://savrn.com/models/wan2-2-14b-i2v-480p-lightning-nsfw-diffusers) Model · Image to video ### [WorldCrafter-Base](https://savrn.com/models/worldcrafter-base) [ARC Lab, Tencent](https://savrn.com/model-publishers/tencentarc) Base transformer weights and their matching camera adapter and LoRA for the WorldCrafter inference code. Place this directory beside WorldCrafter-Fast. Base reads the following shared folders from Fast: repencoder/, textencoder/, tokenizer/, vae/, and scheduler/. Base does not need Fast's transformer or adapter folders. The relative path is configured in inferenceconfig.json. Keep the Base-specific transformer/ and adapter/ together. SHA256SUMS covers the packaged Base files; shared component hashes are recorded in Fast's package. Open weights 14.3B parameters diffusers [View model](https://savrn.com/models/worldcrafter-base) Model · Image to video ### [WorldCrafter-Fast](https://savrn.com/models/worldcrafter-fast) [ARC Lab, Tencent](https://savrn.com/model-publishers/tencentarc) Self-contained weights for WorldCrafter Fast image-to-video, text-to-video, and the interactive image-to-video demo. Use the WorldCrafter inference code and its pinned uv environment. The two transformer branches have independent DMD LoRA and camera adapters. The RepEncoder, text encoder, tokenizer, VAE, and scheduler are included here. No WorldCrafter-Base files are needed for Fast inference. Image-to-video uses five high-noise steps and one low-noise step per chunk. Text-to-video uses four high-noise and eight low-noise steps for the first chunk, then two high-noise and four low-noise steps. Compilation is optional with --enable-compile. inferenceconfig.json resolves shared components… Open weights diffusers [View model](https://savrn.com/models/worldcrafter-fast) ## Questions ### Which Image to video models are most downloaded? By monthly downloads reported by the Hugging Face Hub: Wan_2.2_ComfyUI_Repackaged (8.2M); LTX-2.5 (2.1M); LTX-2.3 (991.2k). ## Other Tasks - [Text Generation](https://savrn.com/models/tasks/text-generation) 1548 - [Image and Text to Text](https://savrn.com/models/tasks/image-and-text-to-text) 577 - [Feature Extraction](https://savrn.com/models/tasks/feature-extraction) 398 - [Robotics](https://savrn.com/models/tasks/robotics) 398 - [Text Classification](https://savrn.com/models/tasks/text-classification) 331 - [Text to Image](https://savrn.com/models/tasks/text-to-image) 232 - [Speech Recognition](https://savrn.com/models/tasks/speech-recognition) 187 - [Text to Speech](https://savrn.com/models/tasks/text-to-speech) 145 - [Image Classification](https://savrn.com/models/tasks/image-classification) 139 - [Audio Classification](https://savrn.com/models/tasks/audio-classification) 130 - [Sentence Similarity](https://savrn.com/models/tasks/sentence-similarity) 103 - [Reinforcement Learning](https://savrn.com/models/tasks/reinforcement-learning) 100 [See all](https://savrn.com/models/tasks)