Tag: comfyui
- ComfyUI on the RX 6800: fixing INT8, GPU VAE decode, and VRAM spill
On Windows, an RX 6800 with local ROCm fixes ran matched ComfyUI image, video, music, and mesh workflows 1.7–3.2 times faster than a Radeon 780M.
- Qwen-Image-2.1 on Radeon 780M: faster images and RGBA sprites
On a Radeon 780M, Qwen-Image-2.1 generated images about 5.5 to 9.3 times faster than Qwen-Image-2512 in this test. It also saved a potion sprite with transparency in the PNG.
- Generating bilingual Open Graph images locally with Qwen-Image
Generating article backgrounds with Qwen-Image-2512 on a Radeon 780M, then adding English and Japanese titles for Astro Open Graph images.
- Splitting LTX-2.5 text encoding: 21 minutes to 37 seconds
The Gemma-4-12B encoder and the diffusion model can't share 14GB of iGPU memory, so ComfyUI runs the encoder on CPU and every new prompt costs 20 minutes before the first frame. Splitting the encode into stable-diffusion.cpp fixes that, once you find the model stage it silently skips.
- Qwen-Image-2512 on the 780M: why ‘Qwen-Image-2.0’ isn’t open-weight
Testing a 20B-class open-weight image model on a Radeon 780M iGPU with no discrete GPU. Qwen-Image-2.0 looked like the obvious pick until it turned out to be API-only. Qwen-Image-2512 is the actual open model, and it runs.
- MiniMax Music 3 on the 780M: local text-to-song generation via ComfyUI
Running MiniMax Music 3, an 8B/0.6B hierarchical autoregressive music model, on a Radeon 780M through ComfyUI. INT8 quantization to fit shared VRAM, hand-wiring the real node graph behind a collapsed UI subgraph, and a ROCm context-poisoning flake caught mid-generation.
- Turning 2D sprites into 3D meshes locally on the Radeon 780M
Turning Craymel Ball's flat 2D sprites into usable 3D character models entirely on a Radeon 780M. TripoSR gets rejected, Hunyuan3D-2mini becomes the first usable tier, and multi-view input on Hunyuan3D-2mv fixes a measured depth-flattening problem that resolution and postprocessing couldn't touch.
- Getting local video generation running on a Radeon 780M mini PC
Running LTX video generation on a Radeon 780M mini PC with no discrete GPU, through a VRAM ceiling, four LTX-2.5 loading bugs, a GGUF quant missing its architecture metadata, and a silently dropped boolean flag that turned coherent video into static noise.
- ComfyUI on AMD Radeon 780M: retiring ZLUDA for AMD's TheRock
AMD's own TheRock build now targets gfx1103 directly, so ComfyUI on a Radeon 780M doesn't need ZLUDA's DLL injection and security exclusions anymore, and it runs roughly twice as fast with the right attention setting.
- Getting real GPU acceleration for Stable Diffusion on an unsupported AMD Radeon 780M
ComfyUI wouldn't touch the GPU on this AMD chip at all. Getting real acceleration meant DirectML, then ZLUDA, and eight separate crashes before Stable Diffusion ran at real speed.
