Text-to-Image
Diffusers
English
lora
flux2
flux2-klein
how-to
instructional
illustrated
illustration
style
Instructions to use devon7y/WikiQwen-Illustrator-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use devon7y/WikiQwen-Illustrator-9B with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.2-klein-base-9B", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("devon7y/WikiQwen-Illustrator-9B") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
WikiQwen-Illustrator-9B: final round-2 weights (step 18000)
Browse files- README.md +3 -4
- pytorch_lora_weights.safetensors +1 -1
README.md
CHANGED
|
@@ -23,8 +23,6 @@ tags:
|
|
| 23 |
|
| 24 |
# WikiQwen-Illustrator-9B
|
| 25 |
|
| 26 |
-
> **Preview weights.** Round 2 at step 6,000 of 18,000 (full ~588k-image set, rank 128). Training continues and the final weights will replace these.
|
| 27 |
-
|
| 28 |
**Give it a caption, get a step illustration.** WikiQwen-Illustrator-9B is the larger sibling of [WikiQwen-Illustrator](https://huggingface.co/devon7y/WikiQwen-Illustrator): a style LoRA for [FLUX.2 [klein] base 9B](https://huggingface.co/black-forest-labs/FLUX.2-klein-base-9B). It turns a one-to-three-sentence scene description into a clean, friendly how-to illustration at 512x384. It is the picture half of WikiQwen: the chat models ([4B](https://huggingface.co/devon7y/WikiQwen-4B), [9B](https://huggingface.co/devon7y/WikiQwen-9B), [35B-A3B](https://huggingface.co/devon7y/WikiQwen-35B-A3B)) write an `[IMAGE: caption]` line above every step, and this LoRA draws it.
|
| 29 |
|
| 30 |
> **Try it first:** [WikiQwen Plus](https://huggingface.co/spaces/devon7y/wikiqwen-plus) (WikiQwen-4B) and [WikiQwen Pro](https://huggingface.co/spaces/devon7y/wikiqwen-pro) (WikiQwen-9B) write an article, then draw every step with this LoRA.
|
|
@@ -116,8 +114,9 @@ Each held-out caption was drawn once and compared with the real illustration for
|
|
| 116 |
|
| 117 |
| Setup | Images | CMMD ↓ | KID ×10³ ↓ | Real-vs-generated probe ↓ | Caption alignment ↑ (generated / real) |
|
| 118 |
| --- | ---: | ---: | ---: | ---: | ---: |
|
| 119 |
-
|
|
| 120 |
-
| 9B round
|
|
|
|
| 121 |
| WikiQwen-Illustrator 4B (round 2 final) | 300 | 0.153 | 70.85 ± 39.05 | 0.970 ± 0.015 | 0.2053 / 0.1965 |
|
| 122 |
| Real vs. real (two halves of the held-out set) | 150 + 150 | 0.041 | -23.53 | 0.5 = chance | 0.1965 (real) |
|
| 123 |
|
|
|
|
| 23 |
|
| 24 |
# WikiQwen-Illustrator-9B
|
| 25 |
|
|
|
|
|
|
|
| 26 |
**Give it a caption, get a step illustration.** WikiQwen-Illustrator-9B is the larger sibling of [WikiQwen-Illustrator](https://huggingface.co/devon7y/WikiQwen-Illustrator): a style LoRA for [FLUX.2 [klein] base 9B](https://huggingface.co/black-forest-labs/FLUX.2-klein-base-9B). It turns a one-to-three-sentence scene description into a clean, friendly how-to illustration at 512x384. It is the picture half of WikiQwen: the chat models ([4B](https://huggingface.co/devon7y/WikiQwen-4B), [9B](https://huggingface.co/devon7y/WikiQwen-9B), [35B-A3B](https://huggingface.co/devon7y/WikiQwen-35B-A3B)) write an `[IMAGE: caption]` line above every step, and this LoRA draws it.
|
| 27 |
|
| 28 |
> **Try it first:** [WikiQwen Plus](https://huggingface.co/spaces/devon7y/wikiqwen-plus) (WikiQwen-4B) and [WikiQwen Pro](https://huggingface.co/spaces/devon7y/wikiqwen-pro) (WikiQwen-9B) write an article, then draw every step with this LoRA.
|
|
|
|
| 114 |
|
| 115 |
| Setup | Images | CMMD ↓ | KID ×10³ ↓ | Real-vs-generated probe ↓ | Caption alignment ↑ (generated / real) |
|
| 116 |
| --- | ---: | ---: | ---: | ---: | ---: |
|
| 117 |
+
| This release: 9B round 2 final (step 18000) | 300 | 0.177 | 33.67 ± 37.13 | 0.968 ± 0.012 | 0.2093 / 0.1965 |
|
| 118 |
+
| Earlier preview: 9B round 2 step 6000 | 300 | 0.182 | 40.52 ± 36.70 | 0.963 ± 0.007 | 0.2097 / 0.1965 |
|
| 119 |
+
| This release drawn at 768x576 (scored after downscaling to 512x384) | 300 | 0.157 | 38.53 ± 36.34 | 0.967 ± 0.014 | 0.2108 / 0.1965 |
|
| 120 |
| WikiQwen-Illustrator 4B (round 2 final) | 300 | 0.153 | 70.85 ± 39.05 | 0.970 ± 0.015 | 0.2053 / 0.1965 |
|
| 121 |
| Real vs. real (two halves of the held-out set) | 150 + 150 | 0.041 | -23.53 | 0.5 = chance | 0.1965 (real) |
|
| 122 |
|
pytorch_lora_weights.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1392551856
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5bd8e878478001bbd7c49a5d4e79502ac90b2f926c5d77564b9b1b7e28456a5
|
| 3 |
size 1392551856
|