VidoGridAll updates
Every frame on the sheet, newest first. Filter by where it came from or by video and image.
Newest first
40 frames- 69NewHunyuanVideo-1.5: Support fp8 gemm with fp8-per-token-sglTencent-Hunyuan/HunyuanVideo-1.5
- 68NewHunyuanVideo-1.5: LoRA loading for generate.pyTencent-Hunyuan/HunyuanVideo-1.5
- 67NewWan2.2: Add LightX2V Community WorksWan-Video/Wan2.2
- 66NewHunyuanVideo-1.5: LoRA tuning scriptTencent-Hunyuan/HunyuanVideo-1.5
- 65NewDiffusers 0.36.0: Pipelines galore, new caching method, training scripts, and more 🎄Diffusers
- 64NewOmniGen2: add OmniGen2-RL for image editingVectorSpaceLab/OmniGen2
- 63Newflux2: FLUX.2 launchblack-forest-labs/flux2
- 62NewRun FLUX.2 on Replicate
FLUX.2 brings professional-grade image generation and editing with unprecedented detail, multi-reference support, and enterprise efficiency.
Replicate Blog - 61NewHow to prompt Nano Banana Pro
Nano Banana Pro brings powerful new capabilities in image generation and editing. Here are the main prompt tricks you should know.
Replicate Blog - 60NewWan2.2: add wan-animate diffusers codeWan-Video/Wan2.2
- 59NewWan2.2: add wan-animate diffusers linksWan-Video/Wan2.2
- 58NewHunyuanImage-3.0: Add vllm dockerfile & Misc improvementsTencent-Hunyuan/HunyuanImage-3.0
- 57NewHow to prompt Veo 3.1
Google's Veo 3.1 brings powerful new video generation capabilities including reference images, first/last frame control, and enhanced image-to-video. Here's everything you need to know.
Replicate Blog - 56NewDiffusers 🐞 fixes for `transformers` models, imports,Diffusers
- 55NewHunyuanImage-3.0: Update deepseek-v3.1 API (#24)Tencent-Hunyuan/HunyuanImage-3.0
- 54NewHunyuanImage-3.0: add rewrite parameters in Command Line ArgumentsTencent-Hunyuan/HunyuanImage-3.0
- 53NewWhich image editing model should I use?
Here is the ultimate comparison post on all the latest image editing models.
Replicate Blog - 52NewQwen-Image: Release Qwen-Image-Edit-2509QwenLM/Qwen-Image
- 51NewQwen-Image: Update Community SupportQwenLM/Qwen-Image
- 50NewFastVideo Release 0.1.6hao-ai-lab/FastVideo
- 49NewQwen-Image-Edit: Image Editing with Higher Quality and Efficiency
QWEN CHAT GITHUB HUGGING FACE MODELSCOPE DISCORD We are excited to introduce Qwen-Image-Edit, the image editing version of Qwen-Image. Built upon our 20B Qwen-Image model, Qwen-Image-Edit successfully extends Qwen-Image’s unique text rendering capabilities to image editing…
Qwen Blog - 48NewFastVideo Release 0.1.5hao-ai-lab/FastVideo
- 47NewQwen-Image: Crafting with Native Text Rendering
GITHUB HUGGING FACE MODELSCOPE DEMO DISCORD We are thrilled to release Qwen-Image, a 20B MMDiT image foundation model that achieves significant advances in complex text rendering and precise image editing. To try the latest model, feel free to visit Qwen Chat and choose “Image…
Qwen Blog - 46NewHow to prompt Veo 3 with images
You'll be surprised what you can do with AI video now.
Replicate Blog - 45NewOpen source video is back
Wan 2.2 is our fastest, cheapest video model.
Replicate Blog
- 44NewLTX-Video: Inference: Integrate fp8 kernelsLightricks/LTX-Video
- 43NewGenerate consistent characters
We compare the best image models for generating consistent characters from a single reference image.
Replicate Blog - 42NewBria is now on Replicate
We've partnered with Bria to bring a suite of commercial-grade image generation and editing models to Replicate. Built entirely on licensed data, Bria’s tools are designed for enterprises and developers building safely with visual AI.
Replicate Blog - 41NewFastVideo v0.1.2hao-ai-lab/FastVideo
- 40NewHow we optimized FLUX.1 Kontext [dev]
A deep-dive into the Taylor Seer optimization technique
Replicate Blog
- 39NewCompare AI video models
It's hard keeping up with every new video model. In this post we'll help you pick the best one for your needs.
Replicate Blog - 38NewOmniGen2: feat: support taylorseerVectorSpaceLab/OmniGen2
- 37NewLTX-Video: sync: Update tests, fp8 configs, and minor fixesLightricks/LTX-Video
- 36NewFastVideo v0.1.1hao-ai-lab/FastVideo
- 35NewThe FLUX.1 Kontext hackathon
We hosted a hackathon with BFL for FLUX.1 Kontext. Here were the winners.
Replicate Blog
- 34NewHow to prompt Veo 3 for the best results
Learn expert prompting techniques to create stunning videos with Google's Veo 3.
Replicate Blog - 33NewGet the most from Google Veo 3
We're sharing our experiments and tips on Google's new Veo 3 model.
Replicate Blog - 32NewMAGI-1: Add support of installing MAGI-1 in ComfyUI via comfy register (#91)SandAI-org/MAGI-1
- 31NewFLUX.1 Kontext from the community
FLUX.1 Kontext is everywhere - see what folks are cooking.
Replicate Blog - 30NewMAGI-1: Add support for comfyui (#82)SandAI-org/MAGI-1