From language to images, open weights to APIs. Understand capabilities and compare real costs.
Find the right engine for your next idea.
Run online:https://www.runninghub.ai/post/2028302502973677570?inviteCode=rh-v1331 Welcome to join our Discord channel for discussion, or contact me to collaborate on custom LoRA builds: https://discord.gg/yVAVa43mWk LoRA can significantly improve Klein consistency without any cue words. Video tutorial: https://youtu.be/JXMbbbdfnSg
This model is trained (code-free!) on ModelScope. Thanks to ModelScope team for providing the training infra: ----- This time, we're bringing you the groundbreaking LoRA light transfer tool. It's the first to solve the problem of Qwen-Edit-2509's inability to perform secondary lighting on images with existing lighting. For communication/cooperation, you can join the discord group to communicate： https://discord.gg/yVAVa43mWk
1. Overall performance was better 2. The brightness of the light can be controlled using the black and white brightness settings shown in Figure 2. 3. The lighting at some angles is still out of control; this will be fixed in the next update. 默认提示词：“使用图2的亮度贴图对图1重新照明(光源来自前方)” 只修改括号内的光源方向即可，例如现在的提示词是“光源来自前方”，可以修改为： 前方、左前方、左方、左后方、后方、右后方、右方、右前方、上方、下方 The default prompt message is: "Relight Figure 1 using the luminance map from Figure 2 (light source from the front)". You only need to modify the light source direction within the brackets. For example, the current prompt message is "light source from the front", which can be changed to: Front, Left Front, Left, Left Rear, Rear, Right Rear, Right, Right Front, Above, Below
client = InferenceClient( provider="wavespeed", api_key=os.environ["HF_TOKEN"], ) image = client.image_to_image( input_image, prompt="Turn the cat into a tiger.", model="dx8152/Qwen-Edit-2509-Multiple-angles", ) This model is trained (code-free!) on ModelScope. Thanks to ModelScope team for providing the training infra: Updated 2025/11/2: Some people mentioned that the model has an unstable consistency issue. I have re-uploaded a version with more training iterations, hoping to fix the consistency problem.
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
My LoRa training is all done using ModelScope. Thanks to the ModelScope team for providing the training infrastructure. Give it a try! There are two ways to use it: 1. Use the prompts in the dataset to change the image directly. 2. Use the trigger word: " 重新照明 "。 （For example:重新照明,使用窗帘透光（柔和漫射）的光线对图片进行重新照明） Meaning: Relighting, using the soft, diffuse light from the curtains to relight the image. （I also uploaded the re-light LoRAs for Kontext downloaded from the Internet. The sources are https://civit.ai/models/1779918 and https://hf.co/dong625/kontext_loras/tree/main ）
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Adjust provider, category or input/output filters. New models are added continuously.
Adjust monthly token usage to compare estimated API costs.
Uses collected, comparable USD-per-million-token rates. Snapshots exclude cache discounts, tiers, extra reasoning output and taxes. Check current source prices.
Separate input, output and cache rates, then estimate the same workload. Image, audio and video rates may use items, duration or resolution rather than tokens.
Not necessarily. Check each version’s license, commercial restrictions and policies. Self-hosting also incurs compute and maintenance costs.
Rankings depend on tasks, versions and methods. Compare accuracy, latency, reliability and costs on your own workload.
