sd3.5 medium gguf
par calcuis
Open source · 5k downloads · 19 likes
1.6
(19 avis)ImageAPI & LocalÀ propos
Le modèle sd3.5 medium gguf est une version optimisée et quantifiée de Stable Diffusion 3.5 Medium, conçue pour générer des images à partir de descriptions textuelles. Il se distingue par sa capacité à fonctionner sur des machines moins puissantes grâce à sa compression, tout en conservant une qualité d'image remarquable. Ses principaux cas d'usage incluent la création artistique, la génération de visuels pour des projets créatifs ou professionnels, et l'expérimentation avec des prompts complexes. Ce qui le rend unique, c'est son équilibre entre performance et accessibilité, permettant une utilisation fluide même sur du matériel ancien, tout en offrant des résultats adaptés à des besoins variés, des projets rapides aux productions plus exigeantes.
Documentation
GGUF quantized version of Stable Diffusion 3.5 Medium
Setup (once)
- drag sd3.5_medium-q5_0.gguf (2.02GB) to > ./ComfyUI/models/unet
- drag clip_g.safetensors (1.39GB) to > ./ComfyUI/models/clip
- drag clip_l.safetensors (246MB) to > ./ComfyUI/models/clip
- drag t5xxl_fp8_e4m3fn.safetensors (4.89GB) to > ./ComfyUI/models/clip
- drag diffusion_pytorch_model.safetensors (168MB) to > ./ComfyUI/models/vae
Run it straight (no installation needed way)
- run the .bat file in the main directory (assuming you are using the gguf-comfy pack below)
- drag the workflow json file (see below) to > your browser
- generate your first picture with sd3, awesome!
Workflows
- example workflow for gguf (if it doesn't work, upgrade your pack: ggc y) 👻
- example workflow for the original safetensors 🎃
Bug reports (or brief review)
- t/q1_0 and t/q2_0; not working recently (invalid GGMLQ type error)
- q2_k is super fast; not usable; but might be good for medical research or abstract painter
- q3 family is fast; finger issue can be easily detected but picture quality is interestingly good
- btw, q3 family is usable; just need some effort on +/- prompt(s); good for old machine user
- notice the same file size in some quantized models; but they are different (according to its SHA256 hash) even they are exactly the same in size; still keep them all here (in full set); see who can deal with it
- q4 and above should be no problem for general-to-high quality production (demo picture shown above generated by just Q4_0 - 1.74GB); and sd team is pretty considerable, though you might not think this model is useful if you have good hardware; imagine you can run it with merely an ancient CPU, should probably appreciate their great effort; good job folks, thumbs up 👍
Upper tier options
References
- base model from stabilityai
- comfyui from comfyanonymous
- gguf node from city96
- gguf-comfy pack
Liens & Ressources