Qwen Image Multiple Angles LoRA is an exquisitely trained LoRA! ๐หโโง๊ฐแ
Keep character and scenes consistent, and flies the camera around! Open source got there! One of the best LoRAs I've come across lately ๐
00:00
apolinario (poli)
4,287 posts
apolinario (poli)
@multimodalart
Joined July 2021
- Boring Reality LoRA just dropped for HunyuanVideo ๐๏ธ๐๏ธ A fine-tune that lead not to cinematic shots, but to something that could've come out of your phone ๐ฑ
00:00 - testing out the Diffusers Image Fill demo capabilities on a random image
00:00 - Google just announced a DALLE-2-like model: Imagen For now no code, just demo site: gweb-research-imagen.appspot.com And paper: gweb-research-imagen.appspot.com/paper.pdf
- Hunyuan-3D-2.1 image-to-3D is now out! โจ Open weights, permissively licensed ๐ 2.1 improves on 2.0 by a LOT in generating high quality textures for the 3D assets ๐ฅ This level of detail from a single image ๐ค๐
00:00 - Apply Texture Qwen Image Edit LoRA by tarn59 works with EVERYTHING! ๐๐ชต๐งถ, this model trains so well I've built this demo so you can apply *any* texture to *any* object on @huggingface
00:00 - I hacked @huggingface Spaces to build an open source @Gradio Dreambooth Training UI that allows you to train a model for less than US$0.80 ๐ฑโ๐ป (you can also use it locally for free): huggingface.co/spaces/multimoโฆ
00:00 - My favorite part is that it works really well with out-of-the-distribution garments
Testing out the new virtual try-on pipeline on @huggingface, IDM-VTON โถ๏ธ huggingface.co/spaces/yisol/Iโฆ - Editing facial expressions in real time now on @huggingface Spaces ๐จโ๐ค๐ A Grog converted Cog image to Gradio running a ComfyUI backend - magic of open source ๐ค โถ๏ธ huggingface.co/spaces/fffilonโฆ
00:00 - Releasing my first FLUX LoRA: FLUX Tarot v1! ๐๐งโโ๏ธ๐ Based on Raider Waite's 1920 tarot (public domain) Model and demo: huggingface.co/multimodalart/โฆ Image & Caption Dataset: huggingface.co/datasets/multiโฆ
- outpainting with the new FLUX-1[dev] Fill model is just on a completely new level ๐ชผ i've built a Space for you to try it๐
GIF - yes! qwen-image excels at following precise rule breaking instructions very few models can do things like "a fried egg with a blue yolk"
A powerful image model knows when/how to break the rules. > a photo of an eye with three separate pupils qwen-image - Introducing Kontext Relight! ๐ก โจ A FLUX Kontext Relight LoRA + demo trained for state-of-the art relighting for subjects & landscapes
00:00 - rejoiced by the rebirth of the skeuomorphic isomorphic 3D icons on @Airbnb I've trained a FLUX LoRA to generate 3D icons in that style
00:00
