forked from lllyasviel/stable-diffusion-webui-forge
-
-
Notifications
You must be signed in to change notification settings - Fork 208
Download Models
Haoming edited this page Jun 28, 2026
·
19 revisions
| Architecture | Checkpoint | UNet / DiT | Text Encoder | VAE |
|---|---|---|---|---|
| SD1 | CivitAI | N/A | N/A | vae-ft-mse-840000 |
| SDXL | CivitAI | N/A | N/A | sdxl-vae-fp16-fix |
| Lumina-Image-2.0 |
gemma_2_2b fp16 |
Flux ae |
||
| Flux-Dev |
t5xxl |
|||
| Flux-Kontext | N/A | |||
| Z-Image |
qwen_3_4b |
|||
| Z-Image-Turbo | ||||
| Flux.2-Klein 4B | ||||
| Flux.2-Klein 9B |
qwen_3_8b |
|||
| Ernie-Image |
ministral-3-3b bf16 |
|||
| Wan 2.2 T2V |
|
umt5_xxl |
wan_2.1_vae | |
| Wan 2.2 I2V |
|
|||
| Qwen-Image |
qwen_2.5_vl_7b |
|||
| Qwen-Image-Edit | ||||
| Anima | bf16 |
qwen_3_0.6b bf16 |
||
| Krea2 |
qwen3vl_4b |
|||
| PiD |
gemma_2_2b_it |
Model Dependent |
Tip
- Put Checkpoint / UNet / DiT in
~webui\models\Stable-diffusion - Put Text Encoders in
~webui\models\text_encoder - Put VAE in
~webui\models\VAE
Note
To use the GGUF version of qwen_2.5_vl_7b for img2img, you need to download and select the mmproj file too
Important
For Nunchaku, download the fp4 version when using a RTX 50+ GPU ; otherwise download the int4 version
Buy me a coffee~ ☕
