ComfyUI

Sure, for a balance between usability and power I'd recommend fooocus. [1] AmuseAI [2] is an alternative that is extremely plug-and-play which can be especially handy with AMD hardware, but is a bit less powerful and also censored by default. ComfyUI [3] is an advanced tool for rich customization and what not. However it's anything but comfy if you're not already quite knowledgeable in this domain - I would not recommend it for a first tool. [1] - https://github.com/lllyasviel/Fooocus [2] - https://github.com/saddam213/AmuseAI [3] - https://github.com/comfy-org/comfyui

So I use a combination of Neo Forge and ComfyUI. Forge has an easier learning curve but ComfyUI gets all the new "hotness" almost immediately since there's so much custom nodes for it. If you're on a Mac, I've heard that Draw Things is supposed to be pretty "batteries included" simple for image gen along the same lines as LM Studio. https://github.com/Haoming02/sd-webui-forge-classic/tree/neo https://github.com/Comfy-Org/ComfyUI https://drawthings.ai

I could see this especially if the tooling gets sharper and we mature beyond full-auto maximum slop per unit time to more reasonable AI-assisted workflows. The difference between the indescribably saccharine images that come out of chat UIs versus watching someone with some artistic skills driving the slick comfyui [0] nodal editor around. I can't unsee echoes of DALE-2 horrors that color my perception of post-2022 digital art, but it will be normal to my kids. [0]: https://github.com/comfy-org/ComfyUI

It could be better sure. In fact I think they use a file called PUT_MODELS_HERE not gitkeep https://github.com/Comfy-Org/ComfyUI/blob/master/models/diff... But in any case, that instruction was already in the readme as well.

i have been testing this on my Framework Desktop. ComfyUI generally causes an amdgpu kernel fault after about 40 steps (across multiple prompts), so i spent a few hours building a workaround here https://github.com/comfyanonymous/ComfyUI/pull/11143 overall it's fun and impressive. decent results using LoRA. you can achieve good looking results with as few as 8 inference steps, which takes 15-20 seconds on a Strix Halo. i also created a llama.cpp inherence custom node for prompt enhancement which has been helping with overall output quality.

It's very likely worth trying ComfyUI on it too: https://github.com/comfyanonymous/ComfyUI Installation instructions: https://github.com/comfyanonymous/ComfyUI#nvidia It's a webUI that'll let you try a bunch of different, super powerful things, including easily doing image and video generation in lots of different ways. It was really useful to me when benching stuff at work on various gear. ie L4 vs A40 vs H100 vs 5th gen EPYC cpus, etc.

https://github.com/comfyanonymous/ComfyUI I only use it on Windows with Nvidia GPU, but it should work both on Windows and Linux with CPU only and with Intel GPUs, as well as on Linux only with AMD. Though skimming the README some more, I also see Apple Silicon section, and one called "DirectML (AMD Cards on Windows)", so maybe AMD+Win works too. As for use: you install ComfyUI from the link above, and then this: https://github.com/ltdrdata/ComfyUI-Manager to have UI for searching and downloading custom nodes (instead of having to install them by hand), and you're good to go.

For runtime, I use ComfyUi [0] which is node based and therefore a bit hard to learn. But you can just look at the examples on their github. Foocus [1] also seems to be popular and a bit more conventional perhaps, though I didn't try it. For models, Flux [2] is pretty good and quite straightforward to use. (In general, you will have a runtime and then you have to get the model weights seperately). Which Flux variant depends on your graphics card, the Flux.1 schnell should work for most decently modern ones. (And the website, civitai.com is a repository for models and other associated tools.) [0] https://github.com/comfyanonymous/ComfyUI [1] https://github.com/lllyasviel/Fooocus [2] https://civitai.com/models/618692?modelVersionId=699279

Didn't believe that anyone would be bridge-burning-happy enough to put this in their official docs, but you're not kidding: https://github.com/comfyanonymous/ComfyUI/wiki/Which-GPU-sho... In retrospect, the fact that Intel and AMD's stock prices both closed slightly up when Microsoft announced the Snapdragon X on Windows 11 was a dead giveaway that the major players knew behind the scenes that it was being released seriously under baked.

I bet you could get this working in https://github.com/comfyanonymous/ComfyUI I have done some other LLava stuff in it

The non standard licensing puts me off in contributing or using this. It is frustrating how the phrase opensource has been diluted in the AI/ML community. ComfyUI has a GPL license [1] while this project uses this [2]. I honestly don't know where I stand since this is a legal document using non-standard phrasing to describe how the rights around the source code. This is a project that uses a custom license with less rights provided than the ComfyUI project it self-describes as improving. Am not sure the title is reflective of the project. [1] - https://github.com/comfyanonymous/ComfyUI/blob/master/LICENS... [2] - https://github.com/6174/comflowyspace/blob/main/LICENSE

Thank you for the support and the valuable feedback! Sorry about the response time, I haven't expected the incoming volume of requests. * For changing prompt in the middle - I'll take a crack at it this week. It's on top of my post launch list. * Feedback button: Thanks for reporting this. The button was supposed to open default email client to email feedback@recurse.chat * LLaVA model: I'll add more documentation. You are right Llava could not generate images. It can only describe images (similar to GPT-4v). For image generation, it's not supported in the app. While I don't have immediate plans for image generation, check out these projects for local image generation. - https://diffusionbee.com/ - https://github.com/comfyanonymous/ComfyUI - https://github.com/AUTOMATIC1111/stable-diffusion-webui

ComfyUI is adding lots of other models. And it's open source and much further along. https://github.com/comfyanonymous/ComfyUI

Check out ComfyUI for a much more advanced and open source version of this. https://github.com/comfyanonymous/ComfyUI