Fix model-card license links for Hugging Face rendering
Browse files- LICENSE.md +2 -2
- README.md +1 -1
- SHA256SUMS +6 -6
- ltx/README.md +3 -3
- ltx/SHA256SUMS +1 -1
- sd35/README.md +3 -3
- sd35/SHA256SUMS +1 -1
LICENSE.md
CHANGED
|
@@ -2,8 +2,8 @@
|
|
| 2 |
|
| 3 |
This model repository contains two PACT adapters with separate governing licenses. There is no single permissive license covering the entire repository.
|
| 4 |
|
| 5 |
-
- **`sd35/`**: the [Stability AI Community License Agreement](sd35/LICENSE), July 5, 2024, governs the SD3.5 derivative adapter, including the PACT authors' LoRA/conditioner modifications. Preserve its [Notice](sd35/Notice), display **Powered by Stability AI**, and comply with the incorporated [Acceptable Use Policy](https://stability.ai/use-policy), including its updates. A readable policy snapshot is included in `sd35/ACCEPTABLE_USE_POLICY.txt`.
|
| 6 |
-
- **`ltx/`**: the [LTX-2 Community License Agreement](ltx/LICENSE), January 5, 2026, governs the LTX derivative adapter, including the PACT authors' modifications. Its full Attachment A, use restrictions, acceptable-use obligations and redistribution terms apply. Preserve [NOTICE](ltx/NOTICE) and the included `ltx/ACCEPTABLE_USE_POLICY.pdf`.
|
| 7 |
|
| 8 |
These copies match the LICENSE files in the pinned base-model repositories used by this release. LTX's pinned README also links a mutable upstream `LICENSE-2_x` page containing a newer agreement; we preserve the pinned repository's actual LICENSE instead of silently substituting that linked text. The included official LTX acceptable-use policy was retrieved on October 12, 2026; its URL is explicitly identified in the newer upstream agreement. The pinned January agreement requires an acceptable-use policy but supplies no separate URL.
|
| 9 |
|
|
|
|
| 2 |
|
| 3 |
This model repository contains two PACT adapters with separate governing licenses. There is no single permissive license covering the entire repository.
|
| 4 |
|
| 5 |
+
- **`sd35/`**: the [Stability AI Community License Agreement](https://huggingface.co/AhmadRH/PACT/blob/main/sd35/LICENSE), July 5, 2024, governs the SD3.5 derivative adapter, including the PACT authors' LoRA/conditioner modifications. Preserve its [Notice](https://huggingface.co/AhmadRH/PACT/blob/main/sd35/Notice), display **Powered by Stability AI**, and comply with the incorporated [Acceptable Use Policy](https://stability.ai/use-policy), including its updates. A readable policy snapshot is included in `sd35/ACCEPTABLE_USE_POLICY.txt`.
|
| 6 |
+
- **`ltx/`**: the [LTX-2 Community License Agreement](https://huggingface.co/AhmadRH/PACT/blob/main/ltx/LICENSE), January 5, 2026, governs the LTX derivative adapter, including the PACT authors' modifications. Its full Attachment A, use restrictions, acceptable-use obligations and redistribution terms apply. Preserve [NOTICE](https://huggingface.co/AhmadRH/PACT/blob/main/ltx/NOTICE) and the included `ltx/ACCEPTABLE_USE_POLICY.pdf`.
|
| 7 |
|
| 8 |
These copies match the LICENSE files in the pinned base-model repositories used by this release. LTX's pinned README also links a mutable upstream `LICENSE-2_x` page containing a newer agreement; we preserve the pinned repository's actual LICENSE instead of silently substituting that linked text. The included official LTX acceptable-use policy was retrieved on October 12, 2026; its URL is explicitly identified in the newer upstream agreement. The pinned January agreement requires an acceptable-use policy but supplies no separate URL.
|
| 9 |
|
README.md
CHANGED
|
@@ -48,6 +48,6 @@ The release adapters were tested with the PACT loaders and representative few-st
|
|
| 48 |
|
| 49 |
## Licenses and attribution
|
| 50 |
|
| 51 |
-
The two adapters have different governing agreements: [SD3.5 Stability AI Community License](sd35/LICENSE) and [LTX-2 Community License](ltx/LICENSE). Read the [license scope](LICENSE.md), [SD3.5 Notice](sd35/Notice) and [LTX NOTICE](ltx/NOTICE) before use. These notices include the authors' permission for their controlled adapter modifications under the corresponding agreement. This repository does not grant rights to the separate base models, text encoders or datasets. The LTX training sources declare noncommercial terms; no blanket commercial-data clearance is asserted.
|
| 52 |
|
| 53 |
**Powered by Stability AI.** SD3.5 is based on Stability AI's Stable Diffusion 3.5 Medium. The audiovisual adapter is a modified derivative of Lightricks' LTX-2.3, using a separate Google Gemma text encoder. These adapters are provided by the PACT authors; upstream attribution does not imply endorsement.
|
|
|
|
| 48 |
|
| 49 |
## Licenses and attribution
|
| 50 |
|
| 51 |
+
The two adapters have different governing agreements: [SD3.5 Stability AI Community License](https://huggingface.co/AhmadRH/PACT/blob/main/sd35/LICENSE) and [LTX-2 Community License](https://huggingface.co/AhmadRH/PACT/blob/main/ltx/LICENSE). Read the [license scope](LICENSE.md), [SD3.5 Notice](https://huggingface.co/AhmadRH/PACT/blob/main/sd35/Notice) and [LTX NOTICE](https://huggingface.co/AhmadRH/PACT/blob/main/ltx/NOTICE) before use. These notices include the authors' permission for their controlled adapter modifications under the corresponding agreement. This repository does not grant rights to the separate base models, text encoders or datasets. The LTX training sources declare noncommercial terms; no blanket commercial-data clearance is asserted.
|
| 52 |
|
| 53 |
**Powered by Stability AI.** SD3.5 is based on Stability AI's Stable Diffusion 3.5 Medium. The audiovisual adapter is a modified derivative of Lightricks' LTX-2.3, using a separate Google Gemma text encoder. These adapters are provided by the PACT authors; upstream attribution does not imply endorsement.
|
SHA256SUMS
CHANGED
|
@@ -1,18 +1,18 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
054b9e6e9d4b8632dd13abe64faded682c344cf9e514813b8d262d0ea94329f1 ltx/ACCEPTABLE_USE_POLICY.pdf
|
| 4 |
e28ef68d90e17b06308e4c5cba5c9a967b70c3d67f87ddc3dfc46a312cb6a134 ltx/LICENSE
|
| 5 |
f8762b60bc5b5383e01000895fde153d4205750c197882e10b5b76d75879f38a ltx/NOTICE
|
| 6 |
-
|
| 7 |
-
|
| 8 |
93af29000f56ba7871b7776db7d7e1702aaebb6e8e1a5fd9db248c23c645ea78 ltx/adapter.yaml
|
| 9 |
64c7d40d520f7f9ec6132c2282d5b9ea521d1eeb5ed609b407cbc1028c88c0e5 ltx/inference.json
|
| 10 |
d4b8626e01f84880976183a2fbc061ba808576a25dfe858f0b84c5aba209867e ltx/lora_weights_step_30000.safetensors
|
| 11 |
667673ea095deb42d7c143b50c61ff7ef941179fc48baf53c1abe41a8a6699da sd35/ACCEPTABLE_USE_POLICY.txt
|
| 12 |
9b60b9d0411f54d4087484ad4acf28ca6fd9f6a84c30ddacb04de2c623254749 sd35/LICENSE
|
| 13 |
212c56d85f751980f710fbe199fe10a047d50782ab3fa3844a30644a339db158 sd35/Notice
|
| 14 |
-
|
| 15 |
-
|
| 16 |
1ebd2ef7643e6bbfd8c3e123c2f3f262c986b2a6f9e5fac0e107902bdeb3f60b sd35/export_validation.json
|
| 17 |
84bab29fdcf94e206a305015c78c2adbfa269a92af01c1aa9a68cb6815323ba9 sd35/flowmap_conditioner.safetensors
|
| 18 |
abd3ccf966654fabe8aadc0c093414c6b9143d2b31840cf84c205b4e6f26c1e8 sd35/flowmap_lora.safetensors
|
|
|
|
| 1 |
+
077eb9ebada7772a8511251c55f42e4340739f6c90ba458968dd34c7f844bcb6 LICENSE.md
|
| 2 |
+
1e451de6612ef5e386028b758627278d2e4ebba87eb0571fa12a0a394cf846c4 README.md
|
| 3 |
054b9e6e9d4b8632dd13abe64faded682c344cf9e514813b8d262d0ea94329f1 ltx/ACCEPTABLE_USE_POLICY.pdf
|
| 4 |
e28ef68d90e17b06308e4c5cba5c9a967b70c3d67f87ddc3dfc46a312cb6a134 ltx/LICENSE
|
| 5 |
f8762b60bc5b5383e01000895fde153d4205750c197882e10b5b76d75879f38a ltx/NOTICE
|
| 6 |
+
0684900b9bc3d482291c005e51215405edb0fc31446c3bcb674e949e0229e46b ltx/README.md
|
| 7 |
+
89947f5fb3bb37c639de74414727c46a3b23b434126a1c7e6ebb4e2671928cdf ltx/SHA256SUMS
|
| 8 |
93af29000f56ba7871b7776db7d7e1702aaebb6e8e1a5fd9db248c23c645ea78 ltx/adapter.yaml
|
| 9 |
64c7d40d520f7f9ec6132c2282d5b9ea521d1eeb5ed609b407cbc1028c88c0e5 ltx/inference.json
|
| 10 |
d4b8626e01f84880976183a2fbc061ba808576a25dfe858f0b84c5aba209867e ltx/lora_weights_step_30000.safetensors
|
| 11 |
667673ea095deb42d7c143b50c61ff7ef941179fc48baf53c1abe41a8a6699da sd35/ACCEPTABLE_USE_POLICY.txt
|
| 12 |
9b60b9d0411f54d4087484ad4acf28ca6fd9f6a84c30ddacb04de2c623254749 sd35/LICENSE
|
| 13 |
212c56d85f751980f710fbe199fe10a047d50782ab3fa3844a30644a339db158 sd35/Notice
|
| 14 |
+
21511466293fbeb84805d6d24b735864da2330ec6116e452e2a561c4a7f25919 sd35/README.md
|
| 15 |
+
35918ed390c9908e1078874582f70ba94decebc67a3805f22a78c4fa5f239a2f sd35/SHA256SUMS
|
| 16 |
1ebd2ef7643e6bbfd8c3e123c2f3f262c986b2a6f9e5fac0e107902bdeb3f60b sd35/export_validation.json
|
| 17 |
84bab29fdcf94e206a305015c78c2adbfa269a92af01c1aa9a68cb6815323ba9 sd35/flowmap_conditioner.safetensors
|
| 18 |
abd3ccf966654fabe8aadc0c093414c6b9143d2b31840cf84c205b4e6f26c1e8 sd35/flowmap_lora.safetensors
|
ltx/README.md
CHANGED
|
@@ -3,7 +3,7 @@ language:
|
|
| 3 |
- en
|
| 4 |
license: other
|
| 5 |
license_name: ltx-2-community-license
|
| 6 |
-
license_link: LICENSE
|
| 7 |
base_model: Lightricks/LTX-2.3
|
| 8 |
base_model_relation: adapter
|
| 9 |
library_name: pytorch
|
|
@@ -55,7 +55,7 @@ For I2V, add an `"image":"/absolute/path/reference.png"` field to a prompt recor
|
|
| 55 |
|
| 56 |
The paper uses 25,000 [VidProM](https://huggingface.co/datasets/WenhaoWang/VidProM) text prompts and 25,000 [TIP-I2V](https://huggingface.co/datasets/WenhaoWang/TIP-I2V) image/prompt cases, with 10% of each task held out. Preparation filters, embeds, clusters, selects and enhances conditions using Gemma. The teacher stores 30-step joint trajectories; PACT learns average velocity with separate masked video/audio losses of equal weight. Training data and Gemma/base weights are not redistributed here.
|
| 57 |
|
| 58 |
-
Both dataset cards declare **CC-BY-NC-4.0**. See [NOTICE](NOTICE) for source attribution and preparation changes. This release is intended for noncommercial research and evaluation and does not assert clearance for commercial use of its training sources. The datasets' terms are distinct from the model agreement; training on them does not by itself establish that every output or adapter inherits a Creative Commons license.
|
| 59 |
|
| 60 |
## Evaluation and limitations
|
| 61 |
|
|
@@ -65,4 +65,4 @@ Generated motion, fine details and composition may differ from the teacher, part
|
|
| 65 |
|
| 66 |
## License
|
| 67 |
|
| 68 |
-
The adapter is distributed under the included **[LTX-2 Community License Agreement](LICENSE), dated January 5, 2026**, exactly as present in the pinned base-model repository. Its full Attachment A, acceptable-use requirements, commercial restrictions and redistribution obligations apply. [NOTICE](NOTICE) contains prominent modification and upstream attribution notices, plus the PACT authors' permission for their controlled adapter modifications subject to that agreement. The separate Gemma encoder is governed by [Gemma terms](https://ai.google.dev/gemma/terms), and dataset licenses remain applicable. This release is not a blanket commercial-use clearance.
|
|
|
|
| 3 |
- en
|
| 4 |
license: other
|
| 5 |
license_name: ltx-2-community-license
|
| 6 |
+
license_link: https://huggingface.co/AhmadRH/PACT/blob/main/ltx/LICENSE
|
| 7 |
base_model: Lightricks/LTX-2.3
|
| 8 |
base_model_relation: adapter
|
| 9 |
library_name: pytorch
|
|
|
|
| 55 |
|
| 56 |
The paper uses 25,000 [VidProM](https://huggingface.co/datasets/WenhaoWang/VidProM) text prompts and 25,000 [TIP-I2V](https://huggingface.co/datasets/WenhaoWang/TIP-I2V) image/prompt cases, with 10% of each task held out. Preparation filters, embeds, clusters, selects and enhances conditions using Gemma. The teacher stores 30-step joint trajectories; PACT learns average velocity with separate masked video/audio losses of equal weight. Training data and Gemma/base weights are not redistributed here.
|
| 57 |
|
| 58 |
+
Both dataset cards declare **CC-BY-NC-4.0**. See [NOTICE](https://huggingface.co/AhmadRH/PACT/blob/main/ltx/NOTICE) for source attribution and preparation changes. This release is intended for noncommercial research and evaluation and does not assert clearance for commercial use of its training sources. The datasets' terms are distinct from the model agreement; training on them does not by itself establish that every output or adapter inherits a Creative Commons license.
|
| 59 |
|
| 60 |
## Evaluation and limitations
|
| 61 |
|
|
|
|
| 65 |
|
| 66 |
## License
|
| 67 |
|
| 68 |
+
The adapter is distributed under the included **[LTX-2 Community License Agreement](https://huggingface.co/AhmadRH/PACT/blob/main/ltx/LICENSE), dated January 5, 2026**, exactly as present in the pinned base-model repository. Its full Attachment A, acceptable-use requirements, commercial restrictions and redistribution obligations apply. [NOTICE](https://huggingface.co/AhmadRH/PACT/blob/main/ltx/NOTICE) contains prominent modification and upstream attribution notices, plus the PACT authors' permission for their controlled adapter modifications subject to that agreement. The separate Gemma encoder is governed by [Gemma terms](https://ai.google.dev/gemma/terms), and dataset licenses remain applicable. This release is not a blanket commercial-use clearance.
|
ltx/SHA256SUMS
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
054b9e6e9d4b8632dd13abe64faded682c344cf9e514813b8d262d0ea94329f1 ACCEPTABLE_USE_POLICY.pdf
|
| 2 |
e28ef68d90e17b06308e4c5cba5c9a967b70c3d67f87ddc3dfc46a312cb6a134 LICENSE
|
| 3 |
f8762b60bc5b5383e01000895fde153d4205750c197882e10b5b76d75879f38a NOTICE
|
| 4 |
-
|
| 5 |
93af29000f56ba7871b7776db7d7e1702aaebb6e8e1a5fd9db248c23c645ea78 adapter.yaml
|
| 6 |
64c7d40d520f7f9ec6132c2282d5b9ea521d1eeb5ed609b407cbc1028c88c0e5 inference.json
|
| 7 |
d4b8626e01f84880976183a2fbc061ba808576a25dfe858f0b84c5aba209867e lora_weights_step_30000.safetensors
|
|
|
|
| 1 |
054b9e6e9d4b8632dd13abe64faded682c344cf9e514813b8d262d0ea94329f1 ACCEPTABLE_USE_POLICY.pdf
|
| 2 |
e28ef68d90e17b06308e4c5cba5c9a967b70c3d67f87ddc3dfc46a312cb6a134 LICENSE
|
| 3 |
f8762b60bc5b5383e01000895fde153d4205750c197882e10b5b76d75879f38a NOTICE
|
| 4 |
+
0684900b9bc3d482291c005e51215405edb0fc31446c3bcb674e949e0229e46b README.md
|
| 5 |
93af29000f56ba7871b7776db7d7e1702aaebb6e8e1a5fd9db248c23c645ea78 adapter.yaml
|
| 6 |
64c7d40d520f7f9ec6132c2282d5b9ea521d1eeb5ed609b407cbc1028c88c0e5 inference.json
|
| 7 |
d4b8626e01f84880976183a2fbc061ba808576a25dfe858f0b84c5aba209867e lora_weights_step_30000.safetensors
|
sd35/README.md
CHANGED
|
@@ -3,7 +3,7 @@ language:
|
|
| 3 |
- en
|
| 4 |
license: other
|
| 5 |
license_name: stabilityai-community-license
|
| 6 |
-
license_link: LICENSE
|
| 7 |
base_model: stabilityai/stable-diffusion-3.5-medium
|
| 8 |
base_model_relation: adapter
|
| 9 |
library_name: pytorch
|
|
@@ -42,7 +42,7 @@ The source README documents CUDA/PyTorch and pinned Diffusers/Transformers depen
|
|
| 42 |
|
| 43 |
## Training data and method
|
| 44 |
|
| 45 |
-
The final method uses raw prompts from [DiffusionDB](https://huggingface.co/datasets/poloclub/diffusiondb) (CC0-1.0) and [Pick-a-Pic v1](https://huggingface.co/datasets/pickapic-anonymous/pickapic_v1) (no license field in the inspected card). Prompts are filtered, clustered and selected without enhancement. A frozen teacher constructs 28-step trajectories; PACT trains destination/guidance conditioning and rank-384 attention LoRA on interval-average velocity plus endpoint MSE. See [Notice](Notice) for pinned source attribution.
|
| 46 |
|
| 47 |
The exact earlier 50k prompt manifest was not preserved in the release. The code reconstructs the selection method without claiming byte-identical historical data. Training data are not redistributed here.
|
| 48 |
|
|
@@ -54,4 +54,4 @@ The adapter inherits base-model biases and limitations. Few-step outputs may dif
|
|
| 54 |
|
| 55 |
## License
|
| 56 |
|
| 57 |
-
The adapter is distributed under the included [Stability AI Community License](LICENSE), dated July 5, 2024, with its incorporated [Acceptable Use Policy](https://stability.ai/use-policy). The license covers LoRA derivatives, requires its attribution and notices on redistribution, and imposes commercial registration/revenue conditions. Read the full terms; this release does not waive them or clear dataset rights. [Notice](Notice) includes the PACT authors' permission for the adapter modifications whose rights they control, subject to that agreement. The separate original PACT code license is not assigned by this model card.
|
|
|
|
| 3 |
- en
|
| 4 |
license: other
|
| 5 |
license_name: stabilityai-community-license
|
| 6 |
+
license_link: https://huggingface.co/AhmadRH/PACT/blob/main/sd35/LICENSE
|
| 7 |
base_model: stabilityai/stable-diffusion-3.5-medium
|
| 8 |
base_model_relation: adapter
|
| 9 |
library_name: pytorch
|
|
|
|
| 42 |
|
| 43 |
## Training data and method
|
| 44 |
|
| 45 |
+
The final method uses raw prompts from [DiffusionDB](https://huggingface.co/datasets/poloclub/diffusiondb) (CC0-1.0) and [Pick-a-Pic v1](https://huggingface.co/datasets/pickapic-anonymous/pickapic_v1) (no license field in the inspected card). Prompts are filtered, clustered and selected without enhancement. A frozen teacher constructs 28-step trajectories; PACT trains destination/guidance conditioning and rank-384 attention LoRA on interval-average velocity plus endpoint MSE. See [Notice](https://huggingface.co/AhmadRH/PACT/blob/main/sd35/Notice) for pinned source attribution.
|
| 46 |
|
| 47 |
The exact earlier 50k prompt manifest was not preserved in the release. The code reconstructs the selection method without claiming byte-identical historical data. Training data are not redistributed here.
|
| 48 |
|
|
|
|
| 54 |
|
| 55 |
## License
|
| 56 |
|
| 57 |
+
The adapter is distributed under the included [Stability AI Community License](https://huggingface.co/AhmadRH/PACT/blob/main/sd35/LICENSE), dated July 5, 2024, with its incorporated [Acceptable Use Policy](https://stability.ai/use-policy). The license covers LoRA derivatives, requires its attribution and notices on redistribution, and imposes commercial registration/revenue conditions. Read the full terms; this release does not waive them or clear dataset rights. [Notice](https://huggingface.co/AhmadRH/PACT/blob/main/sd35/Notice) includes the PACT authors' permission for the adapter modifications whose rights they control, subject to that agreement. The separate original PACT code license is not assigned by this model card.
|
sd35/SHA256SUMS
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
667673ea095deb42d7c143b50c61ff7ef941179fc48baf53c1abe41a8a6699da ACCEPTABLE_USE_POLICY.txt
|
| 2 |
9b60b9d0411f54d4087484ad4acf28ca6fd9f6a84c30ddacb04de2c623254749 LICENSE
|
| 3 |
212c56d85f751980f710fbe199fe10a047d50782ab3fa3844a30644a339db158 Notice
|
| 4 |
-
|
| 5 |
1ebd2ef7643e6bbfd8c3e123c2f3f262c986b2a6f9e5fac0e107902bdeb3f60b export_validation.json
|
| 6 |
84bab29fdcf94e206a305015c78c2adbfa269a92af01c1aa9a68cb6815323ba9 flowmap_conditioner.safetensors
|
| 7 |
abd3ccf966654fabe8aadc0c093414c6b9143d2b31840cf84c205b4e6f26c1e8 flowmap_lora.safetensors
|
|
|
|
| 1 |
667673ea095deb42d7c143b50c61ff7ef941179fc48baf53c1abe41a8a6699da ACCEPTABLE_USE_POLICY.txt
|
| 2 |
9b60b9d0411f54d4087484ad4acf28ca6fd9f6a84c30ddacb04de2c623254749 LICENSE
|
| 3 |
212c56d85f751980f710fbe199fe10a047d50782ab3fa3844a30644a339db158 Notice
|
| 4 |
+
21511466293fbeb84805d6d24b735864da2330ec6116e452e2a561c4a7f25919 README.md
|
| 5 |
1ebd2ef7643e6bbfd8c3e123c2f3f262c986b2a6f9e5fac0e107902bdeb3f60b export_validation.json
|
| 6 |
84bab29fdcf94e206a305015c78c2adbfa269a92af01c1aa9a68cb6815323ba9 flowmap_conditioner.safetensors
|
| 7 |
abd3ccf966654fabe8aadc0c093414c6b9143d2b31840cf84c205b4e6f26c1e8 flowmap_lora.safetensors
|