Instructions to use nodevorg/studio-models-h3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use nodevorg/studio-models-h3 with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Add StudioH3-V1 (int8 convrot)
Browse filesMiniMax H3 derivative under the MiniMax H3 Community License; README and NOTICE updated.
- NOTICE +5 -0
- README.md +13 -2
- diffusion_models/StudioH3-V1.safetensors +3 -0
NOTICE
CHANGED
|
@@ -18,5 +18,10 @@ diffusion_models/minimax_h3_ref2va_hyperflow_flash_int8_convrot_comfy.safetensor
|
|
| 18 |
unchanged.
|
| 19 |
- Every converted tensor was checked against Video Rebirth's Q8_0 GGUF of the same weights.
|
| 20 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
This repository is not an official MiniMax or Video Rebirth product and is not affiliated with or endorsed by either.
|
| 22 |
Powered by MiniMax H3.
|
|
|
|
| 18 |
unchanged.
|
| 19 |
- Every converted tensor was checked against Video Rebirth's Q8_0 GGUF of the same weights.
|
| 20 |
|
| 21 |
+
diffusion_models/StudioH3-V1.safetensors is a Model Derivative of MiniMax-H3 made for studio.no.dev and distributed
|
| 22 |
+
under the same Agreement with no additional terms. Modifications from MiniMax H3 (Section III.2):
|
| 23 |
+
- Weights changed from MiniMax H3 by fine-tuning and model merging, then pruned and quantized to ComfyUI's
|
| 24 |
+
int8_tensorwise + convrot layout.
|
| 25 |
+
|
| 26 |
This repository is not an official MiniMax or Video Rebirth product and is not affiliated with or endorsed by either.
|
| 27 |
Powered by MiniMax H3.
|
README.md
CHANGED
|
@@ -23,9 +23,9 @@ Original model repositories:
|
|
| 23 |
|
| 24 |
## License
|
| 25 |
|
| 26 |
-
|
| 27 |
|
| 28 |
-
[`NOTICE`](NOTICE) lists what changed
|
| 29 |
|
| 30 |
## HyperFlow H3 Flash
|
| 31 |
|
|
@@ -45,3 +45,14 @@ They need [ComfyUI-Studio-HyperFlow](https://github.com/NoDevOrg/ComfyUI-Studio-
|
|
| 45 |
β β βββ minimax_h3_fl2va_hyperflow_flash_int8_convrot_comfy.safetensors
|
| 46 |
β β βββ minimax_h3_ref2va_hyperflow_flash_int8_convrot_comfy.safetensors
|
| 47 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
|
| 24 |
## License
|
| 25 |
|
| 26 |
+
Every file here is a Model Derivative of MiniMax H3 and is distributed under the [MiniMax H3 Community License Agreement](LICENSE) with no additional terms. Video Rebirth distributes HyperFlow H3 Flash under that Agreement, and this repository redistributes it the same way. By downloading or using these files you accept that Agreement, including its territorial restrictions, commercial terms and Acceptable Use Policy. The [upstream LICENSE](https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/LICENSE) governs.
|
| 27 |
|
| 28 |
+
[`NOTICE`](NOTICE) lists what changed in each file. This repository is not an official MiniMax or Video Rebirth product. Powered by MiniMax H3.
|
| 29 |
|
| 30 |
## HyperFlow H3 Flash
|
| 31 |
|
|
|
|
| 45 |
β β βββ minimax_h3_fl2va_hyperflow_flash_int8_convrot_comfy.safetensors
|
| 46 |
β β βββ minimax_h3_ref2va_hyperflow_flash_int8_convrot_comfy.safetensors
|
| 47 |
```
|
| 48 |
+
|
| 49 |
+
## Studio H3 V1
|
| 50 |
+
|
| 51 |
+
`StudioH3-V1.safetensors` (20.2 GB) is a MiniMax H3 checkpoint in ComfyUI's int8 layout (`int8_tensorwise` with convrot, group size 256). It loads with ComfyUI's stock `UNETLoader` (Load Diffusion Model). Use it with the stock MiniMax H3 text encoder and VAEs from [Comfy-Org/MiniMax-H3](https://huggingface.co/Comfy-Org/MiniMax-H3).
|
| 52 |
+
|
| 53 |
+
```
|
| 54 |
+
π ComfyUI/
|
| 55 |
+
βββ π models/
|
| 56 |
+
β βββ π diffusion_models/
|
| 57 |
+
β β βββ StudioH3-V1.safetensors
|
| 58 |
+
```
|
diffusion_models/StudioH3-V1.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3e5fef6bcf2a0c3db46ec61974903d3dcb25ce9b866509b6193fe2f82e9f01e
|
| 3 |
+
size 20197411688
|